Activation velocity

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

• Activationsconcept0.752
  Internal representations of the model on which probes operate; the method uses activations to rank datapoints.
• Activation Compressionconcept0.747
  Key capability: covariance pooling compresses gigabytes of activations into compact stable embeddings without large labeled datasets.
• Activation Steeringmethod0.731
  Causal intervention technique: edit NLA explanation, reconstruct via AR, use difference as steering vector to manipulate model behavior.
• Activation spaceconcept0.721
  Representation space on which linear probes operate to attribute harmful behaviors to training data.
• Activation Probingconcept0.719
  Technique of reading out model beliefs from internal activations before the final answer token is generated
• Activation Correlationmethod0.718
  Pearson correlation of feature activations across 40M tokens used to measure feature similarity and universality across models
• Activation Similarityconcept0.713
  Model-independent feature comparison based on correlating activation vectors across a fixed diverse dataset
• Activation Additionmethod0.712
  Intervention method that adds a learned direction vector to residual stream activations to steer model behavior