Neel Nanda

Neel Nanda is a senior research scientist at Google DeepMind, where he runs the mechanistic interpretability team, as part of artificial general intelligence safety efforts. Prior to this, he performed mechanistic interpretability research at Anthropic under Chris Olah. Nanda has been actively involved in the growth of the mechanistic interpretability research field, from doing some of the early work and making educational materials to supervising junior researchers and creating the TransformerLens library.

IASEAI '25 Sessions

An Introduction to Mechanistic Interpretability

Day
Time
Session ID
Location
Feb 7
2:30–4pm
Track 12
CC7