Inner Workspace Talk Describes Residual Bottlenecks, Not a Global Mind
Read workspace talk as residual bottlenecks, not a psychological workspace. Each layer writes a d_model update; softmax does many-to-few selection.
Category J-Space
Explanations of the J-space, Jacobian lens (J-lens), global workspace theory, how it emerged in training, comparisons to human consciousness/scratchpads/Chain-of-Thought
What the J Lens Protocol Isolates That a Logit Lens Cannot
Isolate causal paths and confirm necessity on residual streams with the J Lens joint lens and first-order Jacobian stack.
How J-space Detects Model Misalignment
In brief J-space detects model misalignment by examining a compact internal workspace in large language models that handles deliberate reasoning, using the…
What Is the Jacobian Lens and How Does It Reveal J-Space?
The Jacobian lens uses input-output Jacobians to find j space, a low-dimensional workspace of verbalizable concepts. How to compute it and what it reveals.
J-Space as a Workspace in Language Models: Insights for Interpretability
How j-space works as a limited-capacity workspace in language models, and what circuit tracing and attribution graphs show about reportable reasoning.