Residual Stream Activation

The intermediate representations in transformer layers whose activations are patched and probed for truth information

Neighborhood — ranked by edge-count

method

Contrastive Activation Steering
uses
Core technique: takes mean difference of model activations on contrastive prompts and adds the resulting vector to the residual stream at inference time.

concept

Residual Stream
related_to
Proposed pathway flowing through layers at each position; calculates K/V values that feed horizontal information flow.
layer 40 residual-stream activations
related_to
The specific neural network layer from which activations are extracted for probe construction and SAE training in the target models

cosine ≥ 0.65 · no typed edge

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

Residual Stream Activation Patchingmethod0.908
Used to localize causally implicated hidden states by swapping activations between true and false inputs
Residual Stream Patchingmethod0.844
Technique to localize causally implicated hidden states by swapping residual stream activations between a true and false input and measuring downstream log-probability changes
Residual Stream Bandwidthconcept0.844
The finite dimensional capacity of the residual stream for storing and communicating information between layers; conceptualized as being under high demand
Residual-Stream Injectionconcept0.837
Core activation intervention: add scaled vector to residual stream at layer l during completion
residual stream recovery trackingmethod0.825
Tracks cosine similarity, norm ratio, and injection direction projection across layers to measure recovery from perturbation
Residual Activation Vectorsconcept0.805
Layer-40 activations with the component explained by compressed Gemini embeddings subtracted, isolating information not driven by surface text content
residual stream recovery dynamicsconcept0.803
The network's tendency to actively attenuate injected perturbations over subsequent layers, erasing the signal before output
Superposition in Residual Streamconcept0.790
The phenomenon where the residual stream communicates many more features than its dimensionality by encoding information across overlapping subspaces