Benchmark-TinyStories-Inpainting Collection Contextual task for Language Feature Visualisation benchmark. • 3 items • Updated Mar 2
Benchmark-TinyStories-Inpainting Collection Contextual task for Language Feature Visualisation benchmark. • 3 items • Updated Mar 2
Benchmark-TinyStories-Inpainting Collection Contextual task for Language Feature Visualisation benchmark. • 3 items • Updated Mar 2
Sandbagging Models Collection Various versions of model organisms that perform sandbagging • 1 item • Updated Mar 2