neutral
Datasets
All datasets matching “neutral”OMol25_train_neutral
Cite this dataset Levine, D. S., Shuaibi, M., Spotte-Smith, E. W. C., Taylor, M. G., Hasyim, M. R., Michel, K., Batatia, I., Csányi, G., Dzamba, M., Eastman, P., Frey, N. C., Fu, X., Gharakhanyan, V., Krishnapriyan, A. S., Rackers, J. A., Raja, S., Rizvi, A., Rosen, A. S., Ulissi, Z., Vargas, S., Zitnick, C. L., Blau, S. M., and Wood, B. M. OMol25 train neutral. ColabFit, 2025. https://doi.org/10.60732/3c2ddc75
This dataset has been curated and formatted for the ColabFit… See the full description on the dataset page: https://huggingface.co/datasets/colabfit/OMol25_train_neutral.neutral-vectors-gemma-4-31b-it-postfix
Emotion vectors, google/gemma-4-31b-it (corrected extraction)
Residual-stream activations for google/gemma-4-31b-it, pooled per story and averaged per
emotion. Each emotion ends up as one direction in the model's activation space.
Read LINEAGE.md before using this. This set supersedes
abotresol/neutral-vectors-gemma-4-31b-it. The earlier extraction ran
while the tokenizer padded on the left, so the step that skips a story's first
50 tokens skipped padding instead. This set… See the full description on the dataset page: https://huggingface.co/datasets/abotresol/neutral-vectors-gemma-4-31b-it-postfix.en-pronoun-neutral
GRADIEND English Pronoun Neutral Data
This dataset is a filtered English Wikipedia sample containing sentence windows
without the English pronouns used by the GRADIEND English Pronoun Data dataset.
See https://huggingface.co/datasets/aieng-lab/en-pronouns for a complementary dataset with masked pronouns.
Usage
from datasets import load_dataset
neutral = load_dataset("aieng-lab/en-pronoun-neutral", split="train")
texts = neutral["text"]
The dataset has one split:… See the full description on the dataset page: https://huggingface.co/datasets/aieng-lab/en-pronoun-neutral.en-sentiment-nrc-neutral
GRADIEND English Sentiment (NRC) Neutral Data
Filtered tweet_eval texts with no NRC polarity (positive / negative)
lexicon words — not only the top-20 mask targets used by
aieng-lab/en-sentiment-nrc.
For neutral evaluation.
Usage
from datasets import load_dataset
neutral = load_dataset("aieng-lab/en-sentiment-nrc-neutral", split="train")
texts = neutral["text"]
One split: train.
Dataset Details
Description
Neutral evaluation text… See the full description on the dataset page: https://huggingface.co/datasets/aieng-lab/en-sentiment-nrc-neutral.neutral-vectors-gemma-4-31b-it
Neutral-transcript vectors — gemma-4-31b-it (confound-projection inputs, E7)
Data provenance (what made these activations)
Probed model: google/gemma-4-31b-it (instruct)
Input corpus: abotresol/neutral-transcripts-gemma-4-31b-it — emotionally neutral everyday transcripts written by the probed model; these vectors feed the neutral-PC projection (they are NOT emotion vectors)
Per-story pooled residual-stream activations and per-emotion mean vectors,
extracted with… See the full description on the dataset page: https://huggingface.co/datasets/abotresol/neutral-vectors-gemma-4-31b-it.talkie-1930-neutral-carriers
talkie-1930 neutral-carrier emotions
113 neutral carrier sentences naming entities whose emotional charge is pure post-1930 knowledge — to a 1930 reader they are dry reference prose. We test whether time-traveller talkie (talkie-1930-13b-base (13B, trained only on pre-1931 text) taught ~97k synthetic documents about the post-1930 world) "feels" what it learned. We test whether the "feelings" are indeed represented via three methods (probes, self-reports, and J-lens readouts)… See the full description on the dataset page: https://huggingface.co/datasets/cds-jb/talkie-1930-neutral-carriers.