2:23:10 How Aligned Is Claude? A Live Review of the Opus 4.5 System Card Neel Nanda 2.1K views - 1 month ago
3:03:21 Bitter Lesson-Pilled Interp: A Live Paper Review (Activation Oracles & PCD) Neel Nanda 3.2K views - 2 months ago
42:21 How Reasoning Models Break Mechanistic Interpretability Techniques Neel Nanda 2.9K views - 2 months ago
2:54:53 What do models learn during finetuning? A model diffing paper walkthrough w/ Clement & Julian Neel Nanda 3.7K views - 3 months ago
59:16 A Walkthrough of Copy Suppression w/ Callum McDougall, Arthur Conmy & Cody Rushing Part 2/3 Neel Nanda 1.6K views - 2 years ago
17:23 A Walkthrough of Copy Suppression w/ Callum McDougall, Arthur Conmy & Cody Rushing Part 3/3 Neel Nanda 477 views - 2 years ago
53:33 A Walkthrough of Copy Suppression w/ Callum McDougall, Arthur Conmy & Cody Rushing Part 1/3 Neel Nanda 1.9K views - 2 years ago
38:10 A Walkthrough of Automated Circuit Discovery w/ Arthur Conmy Part 1/3 Neel Nanda 4.3K views - 2 years ago
44:25 A Walkthrough of Automated Circuit Discovery w/ Arthur Conmy Part 2/3 Neel Nanda 1.4K views - 2 years ago
39:14 A Walkthrough of Automated Circuit Discovery w/ Arthur Conmy Part 3/3 Neel Nanda 799 views - 2 years ago
45:45 Realtime Research Walkthrough: Parenthesis Balancing in 1L Toy Language Model (Part 2) Neel Nanda 848 views - 2 years ago
1:45:54 Realtime Research Walkthrough: Parenthesis Balancing in 1L Toy Language Model (Part 1) Neel Nanda 1.8K views - 2 years ago
32:36 A Walkthrough of Finding Neurons In A Haystack w/ Wes Gurnee Part 1/3 Neel Nanda 2.3K views - 2 years ago
1:04:23 A Walkthrough of Finding Neurons In A Haystack w/ Wes Gurnee Part 2/3 Neel Nanda 942 views - 2 years ago
2:06:02 A Walkthrough of Finding Neurons In A Haystack w/ Wes Gurnee Part 3/3 Neel Nanda 723 views - 2 years ago
30:44 A Walkthrough of Aligning Causal Variables and Distributed Representations w/ Atticus Geiger (1/3) Neel Nanda 2.8K views - 2 years ago
1:04:39 A Walkthrough of Aligning Causal Variables and Distributed Representations w/ Atticus Geiger (2/3) Neel Nanda 1.3K views - 2 years ago
1:35:50 A Walkthrough of Aligning Causal Variables and Distributed Representations w/ Atticus Geiger (3/3) Neel Nanda 1.1K views - 2 years ago
1:19:25 Implementing GPT-2 From Scratch (Transformer Walkthrough Part 2/2) Neel Nanda 20.1K views - 2 years ago
46:08 A Walkthrough of Progress Measures for Grokking via Mechanistic Interpretability: Why? (Part 3/3) Neel Nanda 1.4K views - 2 years ago
40:08 A Walkthrough of Progress Measures for Grokking via Mechanistic Interpretability: How? (Part 2/3) Neel Nanda 2K views - 2 years ago
43:10 A Walkthrough of Progress Measures for Grokking via Mechanistic Interpretability: What? (Part 1/3) Neel Nanda 7.4K views - 2 years ago
1:03:52 A Walkthrough of Reverse-Engineering Modular Addition: Why does it grok? (Part 3/3) Neel Nanda 1.6K views - 2 years ago
1:13:57 A Walkthrough of Reverse-Engineering Modular Addition: The Fourier Multiplication Algorithm Part 2/3 Neel Nanda 2.9K views - 2 years ago
34:38 A Walkthrough of Reverse-Engineering Modular Addition: Model Training (Part 1/3) Neel Nanda 5.6K views - 2 years ago
44:48 Project Advising Call: Memorisation in GPT-2 Small (w/ Tessa Barton + Kushal Jain) Neel Nanda 1.2K views - 3 years ago
2:29:35 A Walkthrough of Toy Models of Superposition w/ Jess Smith Neel Nanda 8.8K views - 3 years ago
1:03:52 A Walkthrough of In-Context Learning and Induction Heads Part 1 of 2 (w/ Charles Frye) Neel Nanda 6.1K views - 3 years ago
1:46:05 A Walkthrough of Interpretability in the Wild Part 2/2: Deep Dive (w/ authors Kevin, Arthur & Alex) Neel Nanda 1.9K views - 3 years ago
57:20 A Walkthrough of Interpretability in the Wild Part 1/2: Overview (w/ authors Kevin, Arthur, Alex) Neel Nanda 6.7K views - 3 years ago
1:38:00 Real-Time Research Recording: Can a Transformer Re-Derive Positional Info? Neel Nanda 7.8K views - 3 years ago
2:50:14 A Walkthrough of A Mathematical Framework for Transformer Circuits Neel Nanda 44.7K views - 3 years ago