method
active
method:activation-oracles-aoActivation Oracles (AO)
Supervised method training models to answer questions about activations; NLAs differ by being unsupervised.
Neighborhood — ranked by edge-count
Papers (2)
paper
Methods (2)
method
- Natural Language Autoencoders (NLAs)associated_withextendsCore unsupervised method for generating natural language explanations of LLM activations through a verbalizer-reconstructor pair trained with RL.
- Evaluation of tool uplift over transcript-only baseline using accuracy and AUROC.
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.
- Framework training LLMs to answer questions about externally-provided activation vectors
- Internal representations of the model on which probes operate; the method uses activations to rank datapoints.
- Defines scope; they cannot answer encoding, geometry, or algorithm questions.
- Argument for scalability.
- Central claim from tl;dr.
- Intervention method that adds a learned direction vector to residual stream activations to steer model behavior
- Overall positioning.
- Large activation magnitudes in the residual stream that Queipo-de Llano et al. link to causing compression behavior and stages of inference