Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
PrototypeCommon

stanfordnlp/axbench

Stanford NLP Python library for benchmarking the utility of LLM interpretability methods

Owner
stanfordnlp (organization)
Stars
Stars: 219
Forks
Forks: 46
Language
Python
License
Apache-2.0
Created
2024
Topics
interpretabilityinterventionlarge-language-modelsllm-steeringmechanistic-interpretability
Tier
Prototype (100 to 249 ★) What this tier means
View on GitHub

More repos by stanfordnlp

All 20 repos by stanfordnlp

Nearby in Python

All Python repos