Hacker News
Linking pages
Linked pages
- Introducing Superalignment https://openai.com/blog/introducing-superalignment 558 comments
- Language models can explain neurons in language models https://openai.com/research/language-models-can-explain-neurons-in-language-models 530 comments
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learning https://transformer-circuits.pub/2023/monosemantic-features/index.html 5 comments
Related searches:
Search whole site: site:github.com
Search title: GitHub - openai/transformer-debugger
See how to search.