Media Summary: Art by Clipped from episode 19 of AXRP: Transcript of that episode: ... This is a talk I gave to my MATS 9.0 training scholars about the big picture of mech interp - as of Oct 2025, what had changed? How can we reverse engineer what a neural network is doing? In this IASEAI '25 session, An Introduction to
What Is Mechanistic Interpretability Neel Nanda Explains - Detailed Analysis & Overview
Art by Clipped from episode 19 of AXRP: Transcript of that episode: ... This is a talk I gave to my MATS 9.0 training scholars about the big picture of mech interp - as of Oct 2025, what had changed? How can we reverse engineer what a neural network is doing? In this IASEAI '25 session, An Introduction to This is a talk I gave to my MATS scholars, with a stylised history of the field of Part 1 of a walkthrough of our paper, Progress Measures for Grokking via Visit our sponsor 80000 hours - grab their free career guide and check out their podcast! Use our ...
What's happening inside an AI model as it thinks? Why are AI models sycophantic, and why do they hallucinate? Are AI models ... How good are we at understanding the internal computation of advanced machine learning models, and do we have a hope at ... A surprising fact about modern large language models is that nobody really knows how they work internally. At Anthropic, the ... A talk I gave to my MATS 9.0 training program about reasoning model See part 2 here: Implementing GPT-2 from Scratch Template notebook: ...
![The Dark Matter of AI [Mechanistic Interpretability]](https://i.ytimg.com/vi/UGO_Ehywuxc/mqdefault.jpg)
![Neel Nanda - Our Pivot To Pragmatic Interpretability [Alignment Workshop]](https://i.ytimg.com/vi/k93o4R145Os/mqdefault.jpg)
