method
active
method:activation-reconstructor-arActivation Reconstructor (AR)
Component of NLA that maps natural language explanations back to activations; truncated to first l layers of target model.
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- Natural Language Autoencoders (NLA)implementsAn unsupervised method for generating natural language explanations of LLM activations through a verbalizer-reconstructor pair trained jointly with RL.
Methods (1)
method
- Natural Language Autoencoders (NLAs)implementsCore unsupervised method for generating natural language explanations of LLM activations through a verbalizer-reconstructor pair trained with RL.
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.
- Internal representations of the model on which probes operate; the method uses activations to rank datapoints.
- Adding steering vector in forward direction to push model activations toward stronger reflective behavior.
- Intervention method that adds a learned direction vector to residual stream activations to steer model behavior
- The conventional approach (e.g., SAEs, transcoders) of decomposing activations into interpretable features.
- Key capability: covariance pooling compresses gigabytes of activations into compact stable embeddings without large labeled datasets.
- Component of NLA that maps activations to text descriptions; initialized as copy of target LLM with supervised warm-start on summarization task.
- Standard method in mechanistic interpretability that intervenes on activations; VPD flips this paradigm by patching parameters.
- Latent model activations when processing inputs framed from another agent's perspective