method
active
method:goodfire-ember-contrastive-searchGoodfire Ember Contrastive Search
API method used to identify latents differentially activated between on-topic and off-topic prompt-response pairs
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- 26 SAE latents identified as differentially activated during off-topic content and causally linked to ESR
Artifacts (1)
artifact
- Goodfire Ember APIimplementsAPI providing contrastive search functionality used to identify off-topic detector latents
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- AI research company; authors' affiliation; develops tools including EVEE and publishes research on genomic foundation models.
- API providing access to sparse autoencoder features for LLaMA 3.3 70B used for feature steering in Experiment 2
- Unsupervised probing method from Burns et al. 2023 that identifies directions along which contrast pair representations are far apart
- Unsupervised probe by Burns et al. to predict latent truth representations; cited as related but limited in generalization
- A pipeline employing controlled semantic oppositions to distill monosemantic functional features from sparse activation spaces.
- The property that living structures contain intense contrast—far more than one imagines helpful; true opposites which annihilate each other when superimposed, creating differentiation that gives birth to something; contrast unifies rather than separates when used correctly
- Method comparing brain activity in conscious vs. unconscious conditions.
- Pairs of prompts at different reflection levels used to compute steering vectors.