4 Philosophies of Interpretability
A talk I gave to my MATS 8.0 training program laying out what I view as the main philosophies and approaches to doing interpretability research, the pros and cons, and the different perspectives they give on standards of evidence and how one might approach a problem.
▶︎
How To Think About Thinking Models
▶︎
What Matters Right Now In Mechanistic Interpretability?
▶︎
10th Faculty Induction Programme (Online) From 09.06.2026 to 09.07.2026
▶︎
How To Interpret Chain Of Thought: A Walkthrough
▶︎
How Reasoning Models Break Mechanistic Interpretability Techniques
▶︎
Neel Nanda: Mechanistic Intepretability (HAAISS 2024)
▶︎
An Introduction to Mechanistic Interpretability – Neel Nanda | IASEAI 2025
▶︎
Why birth rates are falling everywhere all at once | FT
▶︎
Chomsky was wrong.They taught me a lie.
▶︎
Hasan Piker & Yanis Varoufakis | Banned for Insufficient Support of Genocide
▶︎
Classic Debate: Chomsky vs Foucault - on Human Nature (English Dubbed)
▶︎
How Will Mech Interp Help Make AGI Safe?
▶︎
What Happened With Sparse Autoencoders?
▶︎
The French Do Not Care About Work
▶︎
The hidden logic behind #, @, & and §
▶︎
Ontology, epistemology and paradigms – what they are and how to write about them in your PhD thesis
▶︎
Mechanistic Interpretability for NLP: One-stop Guide for Everything you Need to Know
▶︎
How To Think SO CLEARLY People Assume You're A Genius
![The Dark Matter of AI [Mechanistic Interpretability]](https://i.ytimg.com/vi/UGO_Ehywuxc/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLBkSvGfku9uu1v4EkqTxrcfZ6YBMA)
▶︎
The Dark Matter of AI [Mechanistic Interpretability]
▶︎