TM
Tom Mcgrath
Locating
Cross-referencing over 67 channels for appearances
Tom Mcgrath
3
Mentions
192.0K
Views
"Chief Scientist at an unnamed AI organization (likely Anthropic or DeepMind based on context), quoted regarding interpretability."
![[State of MechInterp] SAEs in Production, Circuit Tracing, AI4Science, "Pragmatic" Interp — Goodfire](https://img.youtube.com/vi/CoZp6xaTbWw/mqdefault.jpg)
"Co-founder of Goodfire who previously started the interpretability team at DeepMind."
"Co-founder of Goodfire mentioned in the context of the company's founding."
Arcmira media summary
Arcmira tracks where Tom McGrath appears across indexed YouTube videos, transcripts, channels, and related entities.
Guest on the episode, arguing against the inevitability of extreme power concentration in AI.
Guest on the episode and researcher at Goodfire, explaining technical concepts like backprop and model curvature.
Chief Scientist at Goodfire, guest on the podcast providing technical insights into scaling laws and feature taxonomy.
Guest and co-founder of Goodfire, explaining technical concepts like the logic lens and universality.
Chief Scientist at an unnamed AI organization (likely Anthropic or DeepMind based on context), quoted regarding interpretability.
Arcmira tracks 4 indexed media appearances or mentions for Tom McGrath, tied to source videos, channels, and transcript-derived context.
Arcmira uses indexed YouTube videos and transcripts. Representative source evidence on this page includes "AI in the AM — Week 2 Highlights (June 2026)" with transcript-derived context and links when available.
Tom McGrath is connected to Mechanistic Interpretability, Sparse Autoencoders, Nature in Arcmira's media graph.