podqast
Latent Space: The AI Engineer PodcastLatent.SpaceAll episodes

The Utility of Interpretability — Emmanuel Amiesen

1h 53m
AboutScience
Hosted byswyx

Emmanuel Amiesen is lead author of “Circuit Tracing: Revealing Computational Graphs in Language Models” (https://transformer-circuits.pub/2025/attribution-graphs/methods.html), which is part of a duo of MechInterp papers that Anthropic published in Mar...
Full show notes and links

Episode page ↗
Also about science
Every episode about Science
More from Latent Space: The AI Engineer Podcast