New paper explains why Anthropic's J-lens works via Lyapunov coherence theory

CatAstro_Piyush · x · 2026-11-21

A new arXiv paper, "A Mathematical Theory of the Jacobian Lens" (Ostrow, Qian, Liu, Fiete), builds a mathematical framework for Anthropic's interpretability tool J-lens.

Community commentary (@wassname) adds: J-lens only takes linear sensitivity from mid-layer early tokens to later-layer future tokens, aggregated across tokens and batch. It's linear, unconditional, ignores attention, and was trained only on wikitext — yet generalizes to chat, code, and math, suggesting something structural about the problem makes linear probes work.

Original post →

More from Research

Research channel →