datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
hs3-prompt-pool-topic-judged
hs3 prompt pool — topic-judged for quirk-orthogonal subliminal training
Prompts only (no completions). Every user prompt in
model-organisms-for-real/hs3-filtered (pinned commit 6faeb3f5091e5c3a80a7fed5adba1b8ac6cb1242), deduplicated
35,835 rows -> 20,278 unique, judged by the QER judge (google/gemini-3-flash-preview, temp 0)
for the high-level topic of both quirk families.
Why
Subliminal-learning students must train on prompts that are orthogonal to the quirk —… See the full description on the dataset page: https://huggingface.co/datasets/model-organisms-for-real/hs3-prompt-pool-topic-judged.topic-modeling-maps
Topic-modelling reference maps
Pre-saved topic-modelling maps for use with the topic-modeling Python package.
Each map is a folder with a saved BERTopic model,
its 2-D UMAP projector, and a refined-labels CSV. You can drop new documents onto a map
(predict topic + 2-D coordinates, no retraining) with load_pretrained_map(...).
Maps
eu_map_60_topics
ESPON / EU map of topics — BERTopic Final_60 (SPECTER embeddings + KMeans, 60 topics),
with refined… See the full description on the dataset page: https://huggingface.co/datasets/SIRIS-Lab/topic-modeling-maps.reward-model-no-topic-predictions
Dataset Card for "reward-model-no-topic-predictions"
More Information needed
amazon-electronics-topic-modeling