Chris Olah - Looking Inside Neural Networks with Mechanistic Interpretability Published 2023-09-01 Download video MP4 360p Download video MP4 720p Recommendations 55:27 Open Problems in Mechanistic Interpretability: A Whirlwind Tour 1:52:29 Lightning Talks, Day 2 2:25:52 The spelled-out intro to neural networks and backpropagation: building micrograd 1:08:06 Deep Learning Basics: Introduction and Overview 1:06:02 Jacob Steinhardt - Aligning Massive Models: Current and Future Challenges 49:23 MIT 6.S191 (2022): Convolutional Neural Networks 53:15 Large Language Models and the Future of Programming by Peter Norvig 1:23:15 [PhD Thesis Defense] Charting the Landscapes of Ventral Neural Code on Generative Image Manifolds 18:58 Ilya Sutskever - Opening Remarks: Confronting the Possibility of AGI 49:30 Liquid Neural Networks 39:31 Ajeya Cotra - “Situational Awareness” Makes Measuring Safety Tricky 1:02:50 MIT 6.S191: Recurrent Neural Networks, Transformers, and Attention 25:28 Watching Neural Networks Learn 55:15 Lightning Talks - Day 1 1:42:18 Intro to Machine Learning & Neural Networks. How Do They Work? 29:28 Paul Christiano - How Misalignment Could Lead to Takeover 1:25:16 Lecture 10 - Neural Networks 38:31 Jan Leike - Scaling Reinforcement Learning from Human Feedback 1:20:26 2023 Spatial Biology Workshop Day 1 (8/28) Session 1 3:50:57 How Deep Neural Networks Work - Full Course for Beginners Similar videos 59:34 CS25 I Stanford Seminar 2022 - Transformer Circuits, Induction Heads, In-Context Learning 03:02 0L - Theory [rough early thoughts] 44:54 CVPR'20 iMLCV tutorial: Introduction to Circuits in CNNs by Chris Olah 54:10 Cohere For AI - Community Talks - Catherine Olsson on Mechanistic Interpretability: Getting Started 18:03 1L Attention - Theory [rough early thoughts] 1:58:44 Dario Amodei (Anthropic CEO) - $10 Billion Models, OpenAI, Scaling, & Alignment 28:37 【BAAI】6月10日上午 | Anthropic’s Core Views on AI Safety | Christopher Olah | 2023北京智源大会 39:51 Dan Hendrycks - Surveying Safety Research Directions 2:50:14 A Walkthrough of A Mathematical Framework for Transformer Circuits 43:12 Jesse Hoogland–AI Risk, Interpretability 1:03:52 A Walkthrough of In-Context Learning and Induction Heads Part 1 of 2 (w/ Charles Frye) 40:53 CVPR'20 iMLCV tutorial: Understanding Deep Neural Networks by Ruth C. Fong 22:21 Will AI be the End of us? 1:52:27 Victoria Krakovna–AGI Ruin, Sharp Left Turn, Paradigms of AI Alignment 1:27:46 Graph Neural Networks and Attention model | Prof. Laura Leal-Taixé More results