Tag
Anthropic developed the Jacobian lens (J-lens) to reveal a hidden 'J-space' inside Claude Opus 4.6, offering unprecedented insight into an LLM's internal reasoning process before it outputs tokens. The technique allows monitoring and control of model behavior by surfacing the words the model is about to produce.
An article discussing a new interpretability technique called the Jacobian Lens and the discovery of J-space, a region in LLMs where verbalizable representations form a global workspace, marking a significant advance in understanding LLM reasoning.
A public demo of a Jacobian-lens view of language model representations, inspired by Anthropic's JSpace paper, allowing users to explore model internals across layers and tokens.
The author tested Anthropic's Jacobian Lens on open models, then it evolved into a local-model hallucination router for detecting AI hallucinations.
A developer built Subtext, a tool that visualizes the internal 'silent words' of language models using Anthropic's Jacobian lens, allowing real-time observation of the model's reasoning before it outputs tokens. The tool runs on a single 12GB GPU and streams at full generation speed.