Apr 10, 2024 · Today we're joined by @peterbhase from @uncnlp to discuss mechanistic interpretability, scalable oversight, and how matrix probing techniques ...
Missing: gehrt/ url? q=
Jan 16, 2024 · Peter Hase · @peterbhase. These results are robust across model scale. Easy data and hard data are similarly effective across model sizes. 5/6.
Missing: gehrt/ url? q=
Peter Hase peterbhase. Follow. I am a PhD student in the UNC-NLP group at UNC Chapel Hill. 36 followers · 0 following. Chapel Hill; https://peterbhase.github.io ...
Missing: gehrt/ url? q= twitter.
In order to show you the most relevant results, we have omitted some entries very similar to the 8 already displayed.
If you like, you can repeat the search with the omitted results included. |