Attention Block Output Activation

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Activation Additionmethod0.782
  Intervention method that adds a learned direction vector to residual stream activations to steer model behavior
• Activationsconcept0.775
  Internal representations of the model on which probes operate; the method uses activations to rank datapoints.
• attention computationconcept0.768
  Process using Q, K, V to compute a heat map over K and weighted sum of V.
• attention mechanismconcept0.745
  Core operation in transformers, computing weighted combinations of previous elements
• Activation decompositionconcept0.734
  The conventional approach (e.g., SAEs, transcoders) of decomposing activations into interpretable features.
• Activation Similarityconcept0.734
  Model-independent feature comparison based on correlating activation vectors across a fixed diverse dataset
• Attention Schemaconcept0.730
  A predictive model representing and controlling attention; central to attention schema theory.
• Activation Oracles (AO)method0.729
  Supervised method training models to answer questions about activations; NLAs differ by being unsupervised.