This content will become publicly available on January 22, 2026
Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
- Award ID(s):
- 2019786
- PAR ID:
- 10591596
- Publisher / Repository:
- Open Review
- Date Published:
- Format(s):
- Medium: X
- Location:
- https://openreview.net/forum?id=I4e82CIDxv
- Sponsoring Org:
- National Science Foundation
More Like this
No document suggestions found
An official website of the United States government
