Here are some of the (published) stuff I’ve worked on.

Line of Sight: Line of Sight: On Linear Representations in VLLMs

Achyuta Rajaram, Sarah Schwettmann, Jacob Andreas, and Arthur Conmy

[Paper] [Code]

los_teaser

A Multimodal Automated Interpretability Agent

Tamar Rott Shaham, Sarah Schwettmann, Franklin Wang, Achyuta Rajaram, Evan Hernandez, Jacob Andreas, Antonio Torralba

[Paper] [Code] [Page]

maia_teaser

Automatic Discovery of Visual Circuits

Achyuta Rajaram*, Neil Chowdhury*, Antonio Torralba, Jacob Andreas, Sarah Schwettmann

*indicates equal contribution

[Paper]

acdc_teaser