NeurIPsMay1234/openpi-interpretability-data download history

NeurIPsMay1234/openpi-interpretability-data is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 332 times (56 in the last 7 days), and 552 times in total. It ranks #45,339 among datasets by monthly downloads.

openpi-interpretability-data Interpretability artifacts (activations, conceptors, linear steering vectors, sparse autoencoder vectors and checkpoints) extracted from open vision-language-action (VLA) policy models on the LIBERO, MetaWorld, and RoboCasa benchmarks. This dataset accompanies

Open NeurIPsMay1234/openpi-interpretability-data on Hugging Face