Pinned Loading
Repositories
Showing 10 of 80 repositories
- Edge-Pruning Public
[NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".
princeton-nlp/Edge-Pruning’s past year of commit activity - unintentional-unalignment Public
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
princeton-nlp/unintentional-unalignment’s past year of commit activity
Top languages
Loading…