Media Summary: A Google TechTalk, presented by Neel Nanda, 2023/06/20 Google Algorithms Seminar - ABSTRACT: 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? Join us in this session as we dive into "
Open Problems In Mechanistic Interpretability - Detailed Analysis & Overview
A Google TechTalk, presented by Neel Nanda, 2023/06/20 Google Algorithms Seminar - ABSTRACT: 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? Join us in this session as we dive into " 0:00 Introduction and Agenda 0:40 What is We break down two axes for thinking about How can we look inside neural networks and figure out how they do what they do? This is likely to be very important for alignment ...
Art by Clipped from episode 19 of AXRP: Transcript of that episode: ... How can we reverse engineer what a neural network is doing? In this IASEAI '25 session, An Introduction to Send us Fan Mail ( The advent of highly capable, Moderator: Brian Cheung, MIT Panelists: Tomaso Poggio, MIT; Jacob Andreas, MIT; Eran Malach, Harvard University; Santosh ... Take your personal data back with Incogni! Use code WELCHLABS at the link below and get 60% off an annual plan: ... ... max 20) trying to make research progress on a small
![The Dark Matter of AI [Mechanistic Interpretability]](https://i.ytimg.com/vi/UGO_Ehywuxc/mqdefault.jpg)
