method
active
method:activation-difference-lens-adlActivation Difference Lens (ADL)
Baseline from Minder et al. combining Patchscopes, logit lens and steering.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- PatchscopesusesUnifying framework for inspecting hidden representations of language models via representation interventions
Methods (1)
method
- Logit LensusesUnsupervised interpretability technique that projects activations through unembedding matrix; provides comparison point for NLA approach.
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.
- Adding steering vector in forward direction to push model activations toward stronger reflective behavior.
- Core framing of AOs.
- Implicit modulation.
- Internal representations of the model on which probes operate; the method uses activations to rank datapoints.
- Tuned lens skips to output answers and is best next-token predictor while J-lens has highest KL.finding0.704Comparison.
- Performance gains over CAA in steering tasks.
- Out-of-distribution generalization of SAE features.
- Component of NLA that maps natural language explanations back to activations; truncated to first l layers of target model.