Home » Authors » Mitchell Ostrow, Daoyuan Qian, Toni Liu, Ila Fiete

Mitchell Ostrow, Daoyuan Qian, Toni Liu, Ila Fiete

Public reference bibliography and cataloged PDF materials authored or published by Mitchell Ostrow, Daoyuan Qian, Toni Liu, Ila Fiete.

Found 1 document(s) Page 1 of 1

A Mathematical Theory of the Jacobian Lens

Year: 2026 • Source: arxiv.org • Listed PDF

Recent work from Anthropic introduced a new interpretability tool, called the Jacobian lens (J-lens, Gurnee et al., 2026). This method identified linear directions in the hidden states of frontier language models that ha...