Re:The Geometry of Categorical and Hierarchical Concepts in ...
by 100ideas on Tuesday June 11, 2024 @03:37AM
(#40643600)
reminds me of the anthropic's recent work on identifying the neuron sets that correlate to various semantic concepts in Claude: https://news.ycombinator.com/item?id=40429540 "Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet"
[ Parent
| on HN ]
Re:The Geometry of Categorical and Hierarchical Concepts in ...
by cabidaher on Tuesday June 11, 2024 @04:33AM
(#40643903)
In the same vein, Refusal in LLMs is mediated by a single direction: https://www.lesswrong.com/posts/jGuXSZgv6qfdhMCuJ/refusal-in...
Re:The Geometry of Categorical and Hierarchical Concepts in ...
by szvsw on Tuesday June 11, 2024 @06:55AM
(#40644754)
OpenAI also just published similar work, though Anthropic did beat them to the punch.