dataset
active
dataset:wmdp-bio
Favorite
WMDP-bio
Unlearning forget set/test.
Neighborhood — ranked by edge-count
Papers (1)
paper
SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
mentions
Methods (1)
method
Unlearning evaluation
uses
Conditional negative clamping on WMDP-bio with MMLU retention.