Code for the paper Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models presented as a poster at ICML 2025. Training runs available on W&B: https://wandb.ai/patrickaaleask/itda/overview
-
Notifications
You must be signed in to change notification settings - Fork 3
pleask/itda
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published