# Verbalizable Representations Form a Global Workspace in Language Models

arXiv: https://arxiv.org/abs/2607.15495 · HTML: https://mlsanity.com/paper/2607.15495/

## Key facts

- Cited by 75 papers in the map (data through 14 Oct 2026).
- Builds on 100 of its 171 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Builds on (most cited first, 30 of 100)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Linear Transformers Are Secretly Fast Weight Programmers](https://mlsanity.com/paper/2102.11174/) (2021)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [On the Number of Linear Regions of Deep Neural Networks](https://mlsanity.com/paper/1402.1869/) (2014)
- [DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models](https://mlsanity.com/paper/2309.03883/) (2023)
- [Layer by Layer: Uncovering Hidden Representations in Language Models](https://mlsanity.com/paper/2502.02013/) (2025)
- [Function Vectors in Large Language Models](https://mlsanity.com/paper/2310.15213/) (2023)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)
- [From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step](https://mlsanity.com/paper/2405.14838/) (2024)

## Built on by (most cited first, 30 of 75)

- [Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence?](https://mlsanity.com/paper/2609.01924/) (2026)
- [Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures](https://mlsanity.com/paper/2607.27617/) (2026)
- [The Ignition Is Real, and It Lives at the Readout: Latent composition, difficulty-clocked ignition, and the interface-constituted commit in a recurrent-depth reasoner](https://mlsanity.com/paper/2608.03263/) (2026)
- [Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility](https://mlsanity.com/paper/2608.03930/) (2026)
- [Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives](https://mlsanity.com/paper/2608.26372/) (2026)
- [LastOPD: Taming Collapse in Latent On-Policy Distillation](https://mlsanity.com/paper/2609.28845/) (2026)
- [Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model](https://mlsanity.com/paper/2607.20058/) (2026)
- [Temperature-driven inversion and nonlinear dynamics in ChatGPT-like AIs](https://mlsanity.com/paper/2608.00939/) (2026)
- [Divergent large language model predictions from convergent representations in ambiguous word pairs](https://mlsanity.com/paper/2608.01816/) (2026)
- [Off-Axis, On Purpose: Where a Transformer Computes Concepts and Why it Does So](https://mlsanity.com/paper/2608.10251/) (2026)
- [Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning](https://mlsanity.com/paper/2608.11408/) (2026)
- [Knowing, and Saying It Only When Asked: LLM Endognostics and the Schizognosis of Minerva-7B](https://mlsanity.com/paper/2609.22219/) (2026)
- [Measuring the Assistant's Harmlessness Preferences on the User Turn](https://mlsanity.com/paper/2609.23935/) (2026)
- [PR-OPD: Privileged Representation On-policy Self-Distillation for Agentic Reinforcement Learning](https://mlsanity.com/paper/2609.36642/) (2026)
- [From Dependency to Compositionality: A Neurosymbolic Lifting of LLM Outputs via Combinatory Categorial Grammar](https://mlsanity.com/paper/2607.18961/) (2026)
- [The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoning](https://mlsanity.com/paper/2607.20952/) (2026)
- [Many-body Tipping Dynamics of ChatGPT-like AIs](https://mlsanity.com/paper/2607.25279/) (2026)
- [From Found to Designed: Concepts as a Design Axis for Large Language Models](https://mlsanity.com/paper/2607.26825/) (2026)
- [RepBench: Compiling Benchmarks into Capability Representations for Large Language Models](https://mlsanity.com/paper/2607.28008/) (2026)
- [GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning](https://mlsanity.com/paper/2608.02585/) (2026)
- [The ethics of artificial intelligence in the life sciences: Universality, cultural diversity and an architecture of care](https://mlsanity.com/paper/2608.05436/) (2026)
- [Measuring Concept Content in Text from LLM Activations: ESG Evidence from Concept Vectors and Linear Probes](https://mlsanity.com/paper/2608.07208/) (2026)
- [Backdoor Decontamination Dynamics in LLM Agents](https://mlsanity.com/paper/2608.11295/) (2026)
- [Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form](https://mlsanity.com/paper/2608.15022/) (2026)
- [Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text](https://mlsanity.com/paper/2608.16868/) (2026)
- [J-Miner: Recovering the Decision Logic of Fine-Tuned LLM Classifiers as Compact Rules](https://mlsanity.com/paper/2608.17063/) (2026)
- [Can Large Language Models "Hyper-Thread"?](https://mlsanity.com/paper/2608.22376/) (2026)
- [Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows](https://mlsanity.com/paper/2608.24842/) (2026)
- [Can We Read the Mind of an Audio LLM? A Verbalizable, Multilingual Middle-Layer Workspace](https://mlsanity.com/paper/2608.24958/) (2026)
- [Short Horizons and Sparse Concepts: a Mathematical View of the Readout in the J-lens](https://mlsanity.com/paper/2608.25347/) (2026)

## Abstract (arXiv)

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.