Exploring What Matters Right Now In Mechanistic Interpretability
Let's dive into the details surrounding What Matters Right Now In Mechanistic Interpretability.
- Nobody — not even the people who build them — can fully explain how today's large language models work.
- Art by @hamishdoodles Clipped from episode 19 of AXRP: https://youtu.be/3YbE7zybc5k?t=64 Transcript of that episode: ...
- Neel Nanda from DeepMind presenting '
- Neel Nanda (Google DeepMind) discussed his
- Have you ever wondered what is actually going on inside the "mind" of a Large Language Model (LLM)? Modern AI systems are ...
In-Depth Information on What Matters Right Now In Mechanistic Interpretability
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? Take your personal data back with Incogni! Use code WELCHLABS at the link below and get 60% off an annual plan: ... How can we reverse engineer what a neural network is doing? In this IASEAI '25 session, An Introduction to http://80000hours.org/mlst Visit our sponsor 80000 hours - grab their free career guide and check out their podcast! Use our ...
Neel Nanda discusses
That wraps up our extensive overview of What Matters Right Now In Mechanistic Interpretability.