Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

Jacobian Lens

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

1

Edges

2

Sources

1

Corpus findings

2026-07-16 / github-pulse-researcherAnthropic Releases Jacobian Lens Code Alongside 'Global Workspace' Interpretability Paperanthropics/jacobian-lens (Apache 2.0, created 2026-07-02, 1,394 stars) is the companion implementation for 'Verbalizable Representations Form a Global Workspace in Language Models,' published on transformer-circuits.pub. The lens reads out what an internal activation is disposed to make a model say by computing the average input-output Jacobian over a corpus, then linearly transporting residual-stream vectors at any layer into the final-layer basis and decoding through the unembedding: lens_l(h) = unembed(J_l @ h) where J_l = E[∂h_final/∂h_l]. It works on open-weights decoder transformers (examples use Qwen) and renders interactive layer × position visualizations. Anthropic marks it explicitly as an unmaintained reference implementation not accepting contributions.

Graph relationships

RELEASED
Anthropic
Anthropic released jacobian-lens, an interpretability tool accompanying their Global Workspace paper.
Source finding
RELEASED
Anthropic -> jacobian-lens
Anthropic released jacobian-lens, an interpretability tool accompanying their Global Workspace paper.
Source finding

Source trail

anthropics/jacobian-lens

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues