Neel Nanda from DeepMind presenting 'Mechanistic Interpretability: A Whirlwind Tour' on July 21, 2024 at the Vienna Alignment Workshop. Key Highlights: Grasping AI cognition for alignment Reverse engineering neural networks Safeguarding against deceptive AI systems The Alignment Workshop is a ser
![Atticus Geiger - State of Interpretability & Ideas for Scaling Up [Alignment Workshop]](https://i.ytimg.com/vi/eqZ1iEoor5s/hqdefault.jpg)
21:14
22:48
22:43
30:27
182:48
25:13
44:11
57:02
59:22
58:54
30:28
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hqdefault.jpg)
37:25
59:25
![Neel Nanda - Our Pivot To Pragmatic Interpretability [Alignment Workshop]](https://i.ytimg.com/vi/k93o4R145Os/hqdefault.jpg)
10:20
47:08
53:18
86:48
75:12
![Hoagy Cunningham — Finding distributed features in LLMs with sparse autoencoders [TAIS 2024]](https://i.ytimg.com/vi/HPLIl9ZOpUQ/hqdefault.jpg)
28:49
117:04