Verbalizable Representations Form a Global Workspace in Language Models
Researchers using a new interpretability technique called the Jacobian lens have identified a functional structure in large language models analogous to the global workspace of human consciousness—the J-space. These representations can be reported, deliberately summoned and held, used for intermediate reasoning steps, and passed to arbitrary downstream computations, while automatic processing proceeds without them. The J-space carries coherent content only in an intermediate band of layers, holds tens of concepts at a time, and is broadcast more widely. In alignment audits, it reveals strategic deliberation, evaluation awareness, and misaligned dispositions that never appear in outputs. Post-training installs the Assistant's viewpoint. Counterfactual reflection training improves behavior by training only what a model would say if interrupted. These findings indicate LLMs maintain a privileged set of representations bearing functional hallmarks of conscious access.
-->
[Submitted on 16 Jul 2026]
Title:Verbalizable Representations Form a Global Workspace in Language Models
View a PDF of the paper titled Verbalizable Representations Form a Global Workspace in Language Models, by Wes Gurnee and 15 other authors
View PDF HTML (experimental)
Abstract:Out of everything the human brain processes, only a small fraction is consciously accessible, in the sense of being available for verbal report, deliberate control, and flexible reasoning. In this paper, we present evidence that an analogous functional distinction has emerged in large language models. Using a new interpretability technique, the Jacobian lens, we identify the representations a model is poised to verbalize at any point in its processing. These representations, which we collectively call the J-space, exhibit the functional properties characteristic of a global workspace: their contents can be reported, deliberately summoned and held, used to carry the intermediate steps of silent reasoning, and passed as arguments to arbitrary downstream computations, while automatic processing such as text parsing and routine inference proceeds without them. The J-space also has structural signatures that global workspace theory associates with conscious access: it carries coherent content only in an intermediate band of layers, holds on the order of tens of concepts at a time, and is broadcast by the model's weights more widely than other representations. These properties make it a practical window into a model's unspoken thinking. In alignment audits, it reveals strategic deliberation, evaluation awareness, and trained-in misaligned dispositions that never appear in the model's outputs. We find that post-training installs the Assistant's point of view in the workspace, and we introduce counterfactual reflection training, which improves behavior by training only what a model would say if interrupted and asked to reflect. These results indicate that language models maintain a small, privileged set of representations bearing some of the functional hallmarks of conscious access, and that decoding these representations sheds light on ongoing cognitive processes.
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as: arXiv:2607.15495 [cs.CL]
(or arXiv:2607.15495v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2607.15495
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Wes Gurnee [view email] [v1] Thu, 16 Jul 2026 22:54:30 UTC (11,700 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Verbalizable Representations Form a Global Workspace in Language Models, by Wes Gurnee and 15 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-07
Change to browse by:
cs cs.AI cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)