method
active
method:activation-injection-at-layer-1-residual-streamActivation injection at layer 1 residual stream
Sum activations onto placeholder-token positions in the AO's layer 1 residual stream; prompt specifies source layer.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Framework training LLMs to answer questions about externally-provided activation vectors
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.
- Core activation intervention: add scaled vector to residual stream at layer l during completion
- The specific neural network layer from which activations are extracted for probe construction and SAE training in the target models
- Used to localize causally implicated hidden states by swapping activations between true and false inputs
- The intermediate representations in transformer layers whose activations are patched and probed for truth information
- Design choice to inject CVs at the middle residual layer where stylistic effects are strongest
- Technique of adding control vectors to model hidden states at mid-residual layers without weight updates
- Technique to localize causally implicated hidden states by swapping residual stream activations between a true and false input and measuring downstream log-probability changes
- Proposed pathway flowing through layers at each position; calculates K/V values that feed horizontal information flow.