Global Workspace in LLMs
Free while signed in. Answers cite the passages they came from.
This Anthropic interpretability work gives a mechanistic account of when a model's verbalized reasoning is load-bearing and when it is not. It identifies a small, privileged set of internal representations that behaves like the global workspace some neuroscientists tie to conscious access.
A new lens: The Jacobian lens, or J-lens, surfaces the directions in the residual stream that a model is poised to verbalize at any point, and the collection of these directions is named the J-space.
Workspace-like roles: J-space contents can be reported, deliberately summoned and held, used to carry the intermediate steps of silent reasoning, and passed as arguments to downstream computation, matching the functional signature of a global workspace.
Small but decisive: The J-space accounts for no more than roughly 10% of activation variance and appears mainly in the middle of the network, yet suppressing it leaves the model able to parse input and speak fluently while it loses the ability to perform complex internal reasoning.
Why it matters: For anyone building on chain-of-thought or steering vectors, this clarifies which internal representations actually drive reasoning, and the authors deliberately scope the claim to access, not phenomenal experience.
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack