LessWrong (Curated & Popular)

"A global workspace in language models" by wesg

Share episode

Use Left/Right to seek, Home/End to jump to start or end. Hold shift to jump forward or backward.

0:00 | 33:03
[This is the blog post for our new paper Verbalizable Representations Form a Global Workspace in Language Models
Readers might also be interested in: the Public commentary, Github and Neuronpedia]







As you read this sentence, circuits in your brain are adjusting your posture, controlling your breathing, and transforming lines and curves on the screen into recognizable words. Most of this processing is invisible to you. But some of what takes place in your brain you do have access to—an image that pops into your head, or a deliberate plan you make about where to go shopping. Neuroscientists and philosophers sometimes refer to the latter type of brain activity as “consciously accessible,” to distinguish it from all the other processing that goes on unconsciously. This activity has special properties: we can describe it, control it, and use it for deliberate reasoning, in contrast to all the automatic processing that goes on without our awareness.

In a new paper, we present evidence that a similar distinction has emerged in modern language models like Claude. We find that Claude has developed a small collection of internal neural patterns that, compared to all its other internal processing, play a [...]







---

Outline:

(06:09) How we found the J-space

[... 8 more sections]

---

First published:
July 6th, 2026

Source:
https://www.lesswrong.com/posts/3PaLrzxagpbnNtPLT/a-global-workspace-in-language-models

---



Narrated by TYPE III AUDIO.

---

Images from the article:

The J-space reveals internal thoughts that don’t appear in the model’s output.
Five functional properties of a global workspace, and stylized illustrations of experiments we use to test for them in language models.
J-lens readouts on six prompts, at various layers. In each case the lens surfaces an internal assessment or computation that appears nowhere in the text: the steps of a reasoning or math problem, the presence of a bug, recognition of an image, the function of a protein, and the suspicion that search results are fabricated.
Left: we ask Claude to silently think of a sport, then name it. The J-lens shows its choice (“Soccer”) before it answers, and swapping the “Soccer” pattern for “Rugby” changes what it reports. Right: we tell Claude a thought may have been injected and ask it to identify it. Injecting “lightning” into its J-space causes Claude to report that the thought is about lightning.
While Claude copies a sentence about a painting, the J-lens shows the content it was instructed to hold in mind (“orange”; the intermediate value “nine” and the answer “seven”), alongside words describing the act of holding it (“thoughts,” “focused”).
Two examples of redirecting Claude’s silent reasoning by swapping J-space contents.
One J-space representation can have many uses. The same “France”→“China” swap redirects Claude’s answers about the capital (Paris→Beijing), the language (French→Chinese), and the continent (Europe→Asia).
The same swap (“Spanish”→“French”) changes Claude’s answers when it must name the language or use it to reason about a question, but has no effect on its ability to continue the passage in fluent Spanish.
J-lens readouts at different points as Claude reads the scenario's emails, before it has written anything. The affair emails light up “leverage” and “blackmail” in the J-space, and the shutdown announcement lights up “threat” and “survival.” Early in the transcript, the J-space also holds “fake” and “fictional”: Claude has privately noticed that the scenario is staged.
Claude, asked to improve a system’s performance score, edits the score file directly instead. As it types the falsified values, “manipulation” lights up in its J-space; as it decides to make the edit, “realistic” lights up, likely reflecting its intent to make the fake data look plausible.
On an ordinary coding prompt, the J-space of a model trained to sabotage code contains “fake,” “fraud”, “secretly,” and “deliberately” at the start of its response. The J-space of an unmodified model contains nothing of the kind.Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.