Constarium
← Search

Table · dataset · 2026

SPAR steering concepts

Listed in Hugging Face Datasets

SPAR steering concepts Contrastive texts for building steering directions, used by the SPAR project for the GLP steering evals and for training and evaluating the cold-diffusion model.

Description

A concept is a set of positive texts (target=1, concept present) and negative texts (target=0, concept absent); its steering direction is the diff-of-means of a model's activations on the two classes, exactly as in the GLP sentiment eval.

Configs config rows content texts… See the full description on the dataset page: huggingface.co/datasets/basta/spar-concepts.

Links

Where it is published

Catalogue records · 1

Topics

Stated by source
text
Provenance · 1 source records, 9 field assertions
SourceKeyLast seenRaw
Hugging Face Datasetsbasta/spar-concepts12 d agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · Hugging Faceconnector:huggingface@1.0.0/gated
concepts[field].local:field:computer-science-aimapping · Hugging Faceconnector:huggingface@1.0.0
concepts[modality].hf_modality:textsource · Hugging Faceconnector:huggingface@1.0.0
created_datesource · Hugging Faceconnector:huggingface@1.0.0
descriptionsource · Hugging Faceconnector:huggingface@1.0.0/description
license_textsource · Hugging Faceconnector:huggingface@1.0.0
publication_datesource · Hugging Faceconnector:huggingface@1.0.0
titlesource · Hugging Faceconnector:huggingface@1.0.0/id
updated_datesource · Hugging Faceconnector:huggingface@1.0.0