Benchmark-TinyStories-Inpainting Collection Contextual task for Language Feature Visualisation benchmark. • 6 items • Updated Apr 26, 2025
Benchmark-TinyStories-Inpainting Collection Contextual task for Language Feature Visualisation benchmark. • 6 items • Updated Apr 26, 2025
Sandbagging Models Collection Various versions of model organisms that perform sandbagging • 2 items • Updated Feb 20, 2025