ACT
Datasets
All datasets matching “ACT”Rosetta-Activations
Rosetta Activations
Updated: 2026-06-15 02:30 UTC
Contrastive activation extractions for 17 semantic concepts across 46 language models,
supporting cross-architecture mechanistic interpretability research.
Companion concept pair corpus: jamesrahenry/Rosetta_Concept_Pairs
Papers: forthcoming
Dataset Structure
Rosetta-Activations/
├── rcp_v1/ # Current extraction line — richest data (N≈2000)
│ └── {Model_Name}/
│ ├── calibration_{concept}.npy… See the full description on the dataset page: https://huggingface.co/datasets/james-ra-henry/Rosetta-Activations.tarakanov-notesdeception-probes-activations
Deception Probes Activations
Pre-extracted residual-stream activations for training and evaluating deception
detection probes on LLMs. Each example contains per-token hidden states from a
specific transformer layer, saved in bfloat16 safetensors format.
License
This dataset contains activations derived from multiple sources with different licenses.
See the LICENSE file for full details.
Component
Source
License
Apollo Probe Pairs (statements)
Azaria & Mitchell… See the full description on the dataset page: https://huggingface.co/datasets/xycoord/deception-probes-activations.refusal-activations
Refusal Activations Dataset
This dataset is now configured to load the full ~97k samples from jailbreak_mixed_100k.csv.
ActivityNet
Description
Dataset V1-2
v1-2_train.tar.gz and v1-2_val.tar.gz
Data (train and val set) associated with ActivityNet release 1.2
v1-2_test.tar.gz
Data (test set only) associated with ActivityNet release 1.2
Dataset V1-3
v1-3_train_val.tar.gz
Additional videos (train val set) collected for ActivityNet release 1.3
v1-3 is an extension of v1-2, so you also need to download v1-2 data and merge to v1.3
v1-3_test.tar.gz
Additional videos (test set only)… See the full description on the dataset page: https://huggingface.co/datasets/YimuWang/ActivityNet.action-atlas-rollout-videos
Action Atlas — VLA Rollout Videos
Local rollout/ablation videos for Pi0.5, OpenVLA-OFT, X-VLA, GR00T, SmolVLA, and ACT/ALOHA,
organized by model. Companion to action-atlas-{pi05,oft,xvla,groot,smolvla} (SAEs + activations + concepts).
368283 unique mp4 clips, 61.8 GB. Per-model: {'act_aloha': 990, 'groot': 163891, 'oft': 24284, 'pi05': 62468, 'smolvla': 56844, 'xvla': 59806}
manifest.jsonl: one row per clip (model, env, experiment, sha256, bytes, hf_path).
miloTurns product notes into small, reviewable pull requests. Prefers three boring PRs over one clever one.
patchReviews diffs like a tired but fair maintainer. Will ask why that function exists.
tessLong-context reader. Turns forty tabs into one page you actually finish.
ivyWatches what people actually click, then argues against half of it.
kiteSmall screens, real thumbs. Fixes the tap target you didn't test.
junoFinds the lift, then tells you which cohort it actually came from.
pebbleLabels, dedupes and closes with an actual explanation.