Jing

hij's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted a collection about 1 month ago

TOFU Unlearned Models

Collection

Collection of Phi TOFU models with various configurations • 17 items • Updated Oct 8 • 2

authored 3 papers 5 months ago

Rigorously Assessing Natural Language Explanations of Neurons

Paper • 2309.10312 • Published Sep 19, 2023

A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments

Paper • 2401.12631 • Published Jan 23

pyvene: A Library for Understanding and Improving PyTorch Models via Interventions

Paper • 2403.07809 • Published Mar 12 • 1

authored a paper 6 months ago

RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations

Paper • 2402.17700 • Published Feb 27 • 2