3:03:21Bitter Lesson-Pilled Interp: A Live Paper Review (Activation Oracles & PCD)Neel Nanda4.7k10 mo ago
2:54:53What do models learn during finetuning? A model diffing paper walkthrough w/ Clement & JulianNeel Nanda4.3k1 yr ago
59:16A Walkthrough of Copy Suppression w/ Callum McDougall, Arthur Conmy & Cody Rushing Part 2/3Neel Nanda1.6k2 yr ago
17:23A Walkthrough of Copy Suppression w/ Callum McDougall, Arthur Conmy & Cody Rushing Part 3/3Neel Nanda5122 yr ago
53:33A Walkthrough of Copy Suppression w/ Callum McDougall, Arthur Conmy & Cody Rushing Part 1/3Neel Nanda2.2k2 yr ago
45:45Realtime Research Walkthrough: Parenthesis Balancing in 1L Toy Language Model (Part 2)Neel Nanda1k3 yr ago
1:45:54Realtime Research Walkthrough: Parenthesis Balancing in 1L Toy Language Model (Part 1)Neel Nanda2k3 yr ago
30:44A Walkthrough of Aligning Causal Variables and Distributed Representations w/ Atticus Geiger (1/3)Neel Nanda3.4k3 yr ago
1:04:39A Walkthrough of Aligning Causal Variables and Distributed Representations w/ Atticus Geiger (2/3)Neel Nanda1.7k3 yr ago
1:35:50A Walkthrough of Aligning Causal Variables and Distributed Representations w/ Atticus Geiger (3/3)Neel Nanda1.3k3 yr ago
46:08A Walkthrough of Progress Measures for Grokking via Mechanistic Interpretability: Why? (Part 3/3)Neel Nanda1.5k3 yr ago
40:08A Walkthrough of Progress Measures for Grokking via Mechanistic Interpretability: How? (Part 2/3)Neel Nanda2.2k3 yr ago
43:10A Walkthrough of Progress Measures for Grokking via Mechanistic Interpretability: What? (Part 1/3)Neel Nanda8.4k3 yr ago
1:03:52A Walkthrough of Reverse-Engineering Modular Addition: Why does it grok? (Part 3/3)Neel Nanda1.6k3 yr ago
1:13:57A Walkthrough of Reverse-Engineering Modular Addition: The Fourier Multiplication Algorithm Part 2/3Neel Nanda3.2k3 yr ago
34:38A Walkthrough of Reverse-Engineering Modular Addition: Model Training (Part 1/3)Neel Nanda6.5k3 yr ago
44:48Project Advising Call: Memorisation in GPT-2 Small (w/ Tessa Barton + Kushal Jain)Neel Nanda1.2k3 yr ago
1:03:52A Walkthrough of In-Context Learning and Induction Heads Part 1 of 2 (w/ Charles Frye)Neel Nanda7.3k3 yr ago
1:46:05A Walkthrough of Interpretability in the Wild Part 2/2: Deep Dive (w/ authors Kevin, Arthur & Alex)Neel Nanda2.2k4 yr ago
57:20A Walkthrough of Interpretability in the Wild Part 1/2: Overview (w/ authors Kevin, Arthur, Alex)Neel Nanda7.7k4 yr ago
1:38:00Real-Time Research Recording: Can a Transformer Re-Derive Positional Info?Neel Nanda9k4 yr ago
