Emmanuel Ameisen on LLM Interpretability episode artwork

EPISODE · Oct 2, 2025 · 29 MIN

Emmanuel Ameisen on LLM Interpretability

from Generative AI in the Real World · host O'Reilly

In this episode, Ben Lorica and Anthropic interpretability researcher Emmanuel Ameisen get into the work Emmanuel’s team has been doing to better understand how LLMs like Claude work. Listen in to find out what they’ve uncovered by taking a microscopic look at how LLMs function—and just how far the analogy to the human brain holds.

NOW PLAYING

Emmanuel Ameisen on LLM Interpretability

0:00 29:04

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

Frequently Asked Questions

How long is this episode of Generative AI in the Real World?

This episode is 29 minutes long.

When was this Generative AI in the Real World episode published?

This episode was published on October 2, 2025.

What is this episode about?

In this episode, Ben Lorica and Anthropic interpretability researcher Emmanuel Ameisen get into the work Emmanuel’s team has been doing to better understand how LLMs like Claude work. Listen in to find out what they’ve uncovered by taking a...

Can I download this Generative AI in the Real World episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!