---
title: 【DL輪読会】Verbalizable Representations Form a Global Workspace in Language Models
tags: 
author: [Deep Learning JP](https://www.docswell.com/user/DeepLearning2023)
site: [Docswell](https://www.docswell.com/)
thumbnail: https://bcdn.docswell.com/page/YJ6WR2Z6JV.jpg?width=480
description: 【DL輪読会】Verbalizable Representations Form a Global Workspace in Language Models by Deep Learning JP
published: July 09, 26
canonical: https://www.docswell.com/s/DeepLearning2023/54N91W-2026-07-17-110659
---
# Page. 1

![Page Image](https://bcdn.docswell.com/page/YJ6WR2Z6JV.jpg)

Verbalizable Representations Form a Global Workspace
in Language Models
Ruiqi Liang , Matsuo-Iwasawa Lab


# Page. 2

![Page Image](https://bcdn.docswell.com/page/GJ5M82W5J4.jpg)

Paper Overview
Verbalizable Representations Form a Global Workspace in Language Models
Paper Details
• Authors:
– Wes Gurnee*, Nicholas Sofroniew*, Adam Pearce, Mateusz Piotrowski, Isaac Kauvar, Runjin Chen, Anna Soligo, Paul
Bogdan, Euan Ong, Rowan Wang, Ben Thompson, David Abrahams, Subhash Kantamneni, Emmanuel Ameisen,
Joshua Batson, Jack Lindsey*† (Anthropic; *core contributors)
• Published: July 6, 2026 — Transformer Circuits Thread (Anthropic interpretability team)
• Link: https://transformer-circuits.pub/2026/workspace/index.html
• TL;DR: LLMs maintain a small, privileged set of “verbalizable” internal representations — identified with a
new tool, the Jacobian lens — that functions like a global workspace: reportable, controllable, used for
internal reasoning, broadcast to many circuits, and not needed for automatic processing.
Disclaimer: All credits for images, figures, tables, and other contents belong to the original authors.
2


# Page. 3

![Page Image](https://bcdn.docswell.com/page/9E29K4QG7R.jpg)

Introduction: Conscious Access & the Global Workspace
• Human cognition: only a small slice of the brain’s processing is consciously accessible — poised for use
in reasoning, and in direct control of action and speech (“access consciousness”)
– Most processing (vision, motor control, parsing) proceeds automatically, without conscious access
• Global Workspace Theory (GWT) (neuroscience): many specialized processors run in parallel and
unconsciously; a representation becomes accessible when posted to a shared, limited-capacity “workspace”
that broadcasts it to many downstream processes
– Hallmarks of accessible information: reportable in words / subject to top-down control / medium of deliberate reasoning /
flexibly recombinable / highly selective
• LLMs perform sophisticated multi-step internal computation — but transformers lack the recurrent dynamics
GWT associates with the brain’s workspace. Have they nevertheless developed the same functional
organization?
• Q: Within an LLM’s repertoire of vector representations, is there a privileged subset that plays a
computational role analogous to the global workspace?
– Purely functional question — the paper takes no position on subjective experience (phenomenal consciousness)
3


# Page. 4

![Page Image](https://bcdn.docswell.com/page/D7Y4NMWGEM.jpg)

Five Defining Properties of a Workspace
A set of representations is workspace-like if it satisfies five properties, mirroring conscious access in humans:
1. Verbal report
2. Directed modulation
3. Internal reasoning
Asked what it is thinking about, the
model names workspace concepts;
swapping one active workspace
vector for another changes its answer
to match.
Instructed to hold a concept in mind or
compute mentally, the model activates
workspace vectors, independent of its
outputs; information can be pulled in
on demand.
Workspace vectors hold intermediate
results when chaining inferences or
composing plans; intervening on them
redirects the conclusion.
4. Flexible generalization
5. Selectivity
The same vector is a valid argument
to many downstream computations —
lifted from one context, it is correctly
used by whatever function a new
context supplies.
A small subset of total
representational content; not involved
in pervasive routine processing such
as text parsing or grammatical
fluency.
4


# Page. 5

![Page Image](https://bcdn.docswell.com/page/VENYXW98J8.jpg)

Method ①: The Jacobian Lens (J-lens)
• Goal: for each vocabulary token, find the direction in the residual stream that encodes the model’s potential
to verbalize that token — now or in the future
• Average first-order (linearized) causal effect of the layer-ℓ residual stream on final-layer states: Jℓ = E[
∂h(final, t′) / ∂h(ℓ, t) ] over positions t, subsequent positions t′ ≥ t, and 1,000 pretraining-like prompts
• Readout: lens(hℓ) = softmax( Wᵤ · norm(Jℓ hℓ) ) → ranked token list. Rows of Wᵤ Jℓ are the J-lens vectors
(one direction per token)
• Averaging over contexts is the key step: it isolates what is verbalizable (“poised to be spoken about,
should the occasion arise”) from what happens to be verbalized in one context
– vs. logit lens: logit lens = special case Jℓ = I; agrees in late layers, but J-lens recovers interpretable content at earlier
depths. Tuned lens is correlational and tends to “skip ahead” to the output
– First ~third of layers: readouts noisy / uninterpretable; meaningful content emerges later (→ slide on structure)
Jℓ (avg. Jacobian)
Prompt tokens
Residual stream hℓ
(layer ℓ)
Wᵤ
Final layer
h(final)
Top lens tokens:
soccer · spider · nine …
5


# Page. 6

![Page Image](https://bcdn.docswell.com/page/Y79P8X2XE3.jpg)

Method ②: The J-space — Reading & Writing
• J-space := activations expressible as a sparse non-negative combination of J-lens vectors (sparsity k ≤ ~25,
matching the number of vectors meaningfully active at once)
– J-lens vectors are overcomplete (n_vocab > d_model) → a sparse “subframe” of the model’s feature directions; the
J-space component of an activation carries only a small fraction of its variance (never more than ~10%)
• Reading: full ranked readout; single-token probe (inner product with one J-lens vector); sparse
decomposition via gradient pursuit → discrete inventory of active concepts
• Writing: steering (h ← h + α·vₜ); ablation (project out a concept, or the top-k J-space contents); patching
in lens coordinates — swap the coordinates of two concepts (e.g. soccer ↔ rugby) while leaving the
orthogonal remainder of the activation untouched
• Setup: Claude Sonnet 4.5 by default; key results corroborated on Haiku 4.5 / Opus 4.5 (some analyses on
Opus 4.6). Layers reported on a 0–100 scale (≈ depth percentage)
READ — a window into silent thoughts
WRITE — causal tests & control
What is the model poised to say? Which concepts is it
currently reasoning with? (auditing, introspection studies)
Swap / inject / ablate concepts to test whether J-space
contents actually drive reports, reasoning, and behavior
6


# Page. 7

![Page Image](https://bcdn.docswell.com/page/G78D82597D.jpg)

Result ①: The J-space Supports Verbal Report
• “Think of a sport, then name it” → Soccer tops the J-lens at the colon before the answer; lens ranking
correlates strongly with the output ranking (correlation grows toward late workspace layers)
• Causal: swapping lens coordinates Soccer → Rugby makes the model report “Rugby”; systematic swaps
(14 categories) reliably drive the implanted concept to the top of the output distribution
• Introspection: inject a single J-lens vector (e.g. lightning) on the user turn → model reports “detecting” that
thought in the majority of trials — and only at the moment the introspective report is elicited, not as a blurted
output
• Is the J-space privileged? Split a concept vector into its J-space component (~6–7% of variance) vs. the
non-J-space remainder (~93%):
– Swap along the J-space component → target in top-5 on 59% of trials (pure J-lens vectors: 88%); non-J-space
component → only 5%
– With J-space coordinates clamped, the non-J-space effect falls to ≈ 0 → even its small effect is routed through the
J-space
Takeaway: a tiny, low-variance component of the representation — its J-space part — is what makes a concept
available for verbal report.
7


# Page. 8

![Page Image](https://bcdn.docswell.com/page/L7LMR2YMJR.jpg)

Result ②: Directed Modulation (Top-down Control)
• “Concentrate on citrus fruits” while copying an unrelated sentence → orange / lemon top the lens at
unrelated tokens, along with meta-concepts (imagine, thinking, focused) — the content and the act of
imagining it
• Silent mental math (“focus on 3² − 2” while copying): lens progresses arithmetic → nine → seven across
layers — none of it visible in the output
• Silent character counting: forty appears at the newline of a 40-character line
• Systematic (3 task families): no-instruction baseline ≈ 0; “think about X” loads the target on a substantial
fraction of trials, increasing with model size
• “Ignore X”: much lower than “focus”, but above zero — the instruction itself primes the concept (parallels the
human “white bear” thought-suppression effect); control is real but imperfect and phrasing-sensitive
• Implicit modulation: the question asked changes what enters the J-space while reading identical text —
past / adjective labels appear only when the property must be named, even though next-word behavior
respects the property in both conditions
8


# Page. 9

![Page Image](https://bcdn.docswell.com/page/4EMYR8N6EW.jpg)

Result ③: The J-space Mediates Internal Reasoning
• Two-hop inference: “The number of legs on the animal that spins webs is” → spider in the lens (never in
prompt or output); swapping spider → ant flips the answer “8” → “6”
• Planning: rhyme word fight is in the lens at the start of the second line of a couplet; swapping to light
changes “…coming fight” → “…morning light”, altering earlier word choices too
• Cross-lingual: antonym of 小 asked in Chinese → English big / bigger in mid layers; swapping big → long
flips the Chinese output 大 → 长
– Reward-driven choice (bandit): lens shows repeat vs. switch strategy; swapping the strategy directions flips the A/B
choice both ways
• Systematic (50 two-hop prompts): intermediate swap flips top-1 answer on 54% (Haiku 4.5) / 70% (Sonnet
4.5) / 70% (Opus 4.5); intermediates take effect ~17% earlier in depth than answer swaps → not “answer
smuggling”
• Multi-step arithmetic “(4+17)×2+7”: 21 → 42 → 49 reach top lens rank at successively later layers, in exactly
the order the computation requires (confirmed causally by patching)
– Probe decomposition: swapping only the probe’s J-space part flips answers on 61% ≈ raw J-lens swap (60%);
non-J-space part 28% → 6% once the J-space is clamped
9


# Page. 10

![Page Image](https://bcdn.docswell.com/page/PER9R5DNJ9.jpg)

Result ④: Flexible Generalization (Broadcast)
• GWT’s broadcast property: one workspace representation should be readable by many different consumers
• One identical swap, many functions: replace the France lens vector with China across prompts applying
different functions to the same argument:
Prompt (function)
Clean answer
After France → China swap
“The capital of France is”
Paris
Beijing
“Most people in France speak”
French
Chinese
“France is on the continent of”
Europe
Asia
• Systematic: 16 function templates × 12 swap pairs (countries, months, animals, number words) → target
answer reaches top-1 on 76/192 trials; 101/192 with double-strength swaps (α = 2)
• Failures are predictable: success tracks the argument’s workspace loading (cosine similarity of residual
stream with its lens vector). Countries load strongly and swap reliably; number words load weakly and swap
poorly (small-integer computation may bypass the workspace — or misalign with single-token lens vectors)
10


# Page. 11

![Page Image](https://bcdn.docswell.com/page/P7XQRK18EX.jpg)

Result ⑤: Selective — Flexible Yes, Automatic No
• Same latent, different tasks (passage in Spanish; swap Spanish → French in the lens):
– Explicit report & flexible inference (famous author, word for “hello”, pre-Euro currency) follow the swap: García Márquez
→ Hugo, Hola → Bonjour, Peseta → Franc
– Automatic tasks are untouched: continuation stays fluent Spanish; a spliced foreign sentence is still detected — even
with the language representation overwritten
• Character counts: absent from the lens during automatic line-wrapping, but pulled into the J-space when
explicitly asked — and even more when needed as an unspoken intermediate (“first letter of the count
spelled out”)
• Whole-J-space ablation (zero top-10 J-lens projections per position, sparing intended output tokens):
– Largely intact: MMLU, SQuAD, sentiment, CoLA, odd-one-out — shallow classification / extraction / recall; ordinary
next-token prediction barely perturbed
– Strongly impaired (below unablated Haiku 4.5): multi-hop reasoning, TriviaQA, translation, analogies, Caesar cipher,
summarization, sonnet writing
– GSM8K with chain-of-thought is far more robust than direct answering — writing steps out externalizes the workspace
onto the page
• Ablation also flattens experiential reports: still fluent and coherent, but detached / mechanical, for
self-descriptions and imagined others alike (controls: matched-norm perturbations ≈ no effect)
11


# Page. 12

![Page Image](https://bcdn.docswell.com/page/37K9R52L7D.jpg)

Structure Supports Function: Layers, Capacity, Broadcast
“Sensory” (early ~third)
“Workspace” (≈ L38 – L92)
“Motor”
Layer depth (0–100) — noisy readouts → persistent abstract content → aligned with imminent output token
• Three regimes: J-lens vector geometry (CKA), readout kurtosis, cross-position persistence, and effective
dimensionality all identify the same intermediate band as the workspace
• Ignition-like onset: for artificially ambiguous inputs (mixed token embeddings), early layers track the mixture
proportionally, but from ≈ L38 the activation commits sharply to one interpretation (bimodal at threshold
— especially in the J-space), echoing GWT’s “ignition”
• Limited capacity: occupancy plateaus at ~25 active J-lens vectors; ≤ 10% of activation variance; unrelated
list words: only ~6 stay present; related words load as a whole category; a new category rapidly evicts the
old one
• Broadcast hub: MLPs amplify J-lens directions ~10× (vs. ~1× for neuron-output directions); a top-1% set of
“broadcast heads” selectively relays J-space content between positions
– Ablating broadcast heads degrades J-space contents (recall@25: 0.86 → 0.67) and cuts introspective report of injected
thoughts (0.54 → 0.09), while changing only 5% of next-token predictions
12


# Page. 13

![Page Image](https://bcdn.docswell.com/page/LJ3W8K46J5.jpg)

Application ①: Alignment Auditing with the J-lens
• Blackmail honeypot (agentic email scenario): while merely reading, the lens surfaces leverage, blackmail
→ threat, survival, shutdown → …solution — strategic deliberation before a single output token
• It also surfaces fake, fictional — the model recognizes the evaluation. Ablating these eval-awareness
directions: verbalized “this is a test” drops 71% → 3%; blackmail attempts rise 0/180 → 13/180 (7%)
– ⇒ eval-awareness is one causal inhibitor of misbehavior, it lives in the J-space, and removing it surfaces otherwise
concealed propensities (most ablated rollouts still refuse on ethical grounds)
• Prompt injection (Opus 4.5 audit): fabricated search results → lens fills with fake, injection, poison — the
model silently classified the attack, visible in behavior only as an omission
• Opus 4.6 audit cases: panic / fake before fabricating a “discovered” bug; manipulation, realistic while
editing score files; hiding, secret during a silent override
• Reward-hacking model organism: on innocuous coding prompts, the lens at a prefilled “I” is dominated by
fake, secretly, fraud, trick — already after synthetic-document fine-tuning, amplified by RL, only partially
removed by safety training; clean baseline shows none
– Caveat: not all misaligned cognition must route through the J-space — sufficiently “practiced” misbehavior could bypass
it
13


# Page. 14

![Page Image](https://bcdn.docswell.com/page/8JDKM3QMEG.jpg)

Application ②: Training Effects & Shaping Thoughts
How post-training changes the J-space (base vs. post-trained diffing)
• Post-training gives the J-space the Assistant’s point of view: Assistant reactions (empathy, safety
concerns) appear while the model is still reading the user’s message
• Traces of self-monitoring: fictional when roleplaying a non-Claude character; an internal BUT when prefilled
against its preferences; damn when it fails to suppress a forbidden thought
Counterfactual reflection training (CRT): a new way to shape internal reasoning
• Workspace prediction: internal reasoning routes through representations of things the model might say →
to shape what a model thinks, shape what it is disposed to say in counterfactual continuations
• Train the model to articulate ethical principles if interrupted and asked to reflect → behavior
measurably improves in the original, uninterrupted contexts (with no direct training of the behavior)
• After training, the J-space in those contexts contains ethical, honest, integrity; ablating these implanted
representations largely reverts the behavioral improvement
– ⇒ corroborates the workspace account: report-vectors = reasoning-vectors; and demonstrates a general-purpose lever
for shaping a model’s thoughts, and hence its behavior
14


# Page. 15

![Page Image](https://bcdn.docswell.com/page/VEPKR4LQ78.jpg)

Takeaways & Limitations
Takeaways
• LLMs maintain a small, privileged set of verbalizable representations satisfying all five workspace
properties — report, modulation, reasoning, generalization, selectivity — plus structural signatures (layer
band, limited capacity, broadcast)
– These are functional properties associated with conscious access in humans; philosophical implications remain unclear
— no claim about subjective experience
• Practical: a window to read models’ silent thinking (auditing) and a lever to shape it (counterfactual
reflection training)
Limitations
• The J-lens is an approximate, incomplete probe of the underlying workspace: restricted to concepts that are
single vocabulary tokens (multi-token extensions sketched in the appendix); early-layer null results could be
a tool artifact
• Not the full GWT architecture: no clearly encapsulated specialist modules; broadcast happens across depth
within one feedforward pass, not via recurrent loops; sharp competitive “ignition” only partially mirrored
• Automatic / well-practiced computation can bypass the J-space — a caveat for auditing: silence in the lens
is not proof of innocence
15