Reading Guide & Overview
Scaling Interpretability Information Center
Get comprehensive updates, key reports, and detailed insights compiled from verified editorial sources.
Search Coverage: Scaling Interpretability
Video Highlights & Reports
Below is a handpicked selection of video coverage regarding Scaling Interpretability.
Scaling interpretability
34,056 views • Live Report
![Atticus Geiger - State of Interpretability & Ideas for Scaling Up [Alignment Workshop]](https://ytimg.googleusercontent.com/vi/eqZ1iEoor5s/mqdefault.jpg)
Atticus Geiger - State of Interpretability & Ideas for Scaling Up [Alignment Workshop]
888 views • Live Report
![The Dark Matter of AI [Mechanistic Interpretability]](https://ytimg.googleusercontent.com/vi/UGO_Ehywuxc/mqdefault.jpg)
The Dark Matter of AI [Mechanistic Interpretability]
285,234 views • Live Report
Eric Michaud—Scaling, Grokking, Quantum Interpretability
1,358 views • Live Report
History
Stay updated on Scaling Interpretability's latest milestones.
Background to Scaling Interpretability
Science and engineering are inseparable. Our researchers reflect on the close relationship between scientific and engineering ... Atticus Geiger from Pr(Ai)²R Group explores “State of Take your personal data back with Incogni! Use code WELCHLABS at the link below and get 60% off an annual plan: ... Eric is a PhD student in the Department of Physics at MIT working with Max Tegmark on improving our scientific/theoretical ... How can we reverse engineer what a neural network is doing? In this IASEAI '25 session, An Introduction to Mechanistic ... Lex Fridman Podcast full episode: Thank you for listening ❤ our ...
Part 1 of a walkthrough of our paper, Progress Measures for Grokking via Mechanistic A surprising fact about modern large language models is that nobody really knows how they work internally. At Anthropic, the ... Eric Michaud returns to the stream to talk about his recent work on This has been my favorite video so far to make! I think At an Anthropic Research Salon event in San Francisco, four of our researchers—Alex Tamkin, Jan Leike, Amanda Askell and ... What's happening inside an AI model as it thinks? Why are AI models sycophantic, and why do they hallucinate? Are AI models ...
Important Facts
Explore the main sources for Scaling Interpretability.
This talk was recorded at NDC AI in Oslo, Norway. Attend the next NDC ...
Deep Dive
Data is compiled from public records and verified media reports.
Last Updated: June 12, 2026
Future Outlook
For 2026, Scaling Interpretability remains one of the most talked-about profiles.
Disclaimer:
Scaling interpretability
![Atticus Geiger - State of Interpretability & Ideas for Scaling Up [Alignment Workshop]](https://i0.wp.com/ytimg.googleusercontent.com/vi/eqZ1iEoor5s/mqdefault.jpg?resize=320,180)
Atticus Geiger - State of Interpretability & Ideas for Scaling Up [Alignment Workshop]
![The Dark Matter of AI [Mechanistic Interpretability]](https://i0.wp.com/ytimg.googleusercontent.com/vi/UGO_Ehywuxc/mqdefault.jpg?resize=320,180)
The Dark Matter of AI [Mechanistic Interpretability]
Eric Michaud—Scaling, Grokking, Quantum Interpretability
An Introduction to Mechanistic Interpretability – Neel Nanda | IASEAI 2025
Mechanistic Interpretability explained | Chris Olah and Lex Fridman
A Walkthrough of Progress Measures for Grokking via Mechanistic Interpretability: What?
Interpretable vs Explainable Machine Learning
What is interpretability?
Interpretability and AI Scaling with Eric Michaud
Scaling Laws of AI explained | Dario Amodei and Lex Fridman
Scaling AI Interpretability. #artificialintelligance #aiinterpretability #aitalk
Jenn Wortman Vaughan: Manipulating and Measuring Model Interpretability
AISOC Workshop: Scaling Machine Learning Reliability with Interpretability - Serg Masis
A Window Into LLMs | Sparse Autoencoders Explained
How difficult is AI alignment? | Anthropic Research Salon
Interpretability: Understanding how AI models think
Between the Layers– Interpreting Large Language Models - Michelle Frost - NDC AI 2025
How Interpretable Features in Claude 3 Work
