method
active
method:w-tw-visualizationW^TW visualization
Visualizes feature interference matrix.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Toy Models of Superpositionmentions
Frameworks (1)
framework
- x'=ReLU(W^TWx+b), main model demonstrating superposition.
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.
- Method of optimizing input to cause a neuron to fire maximally, used to characterize what a neuron detects; establishes causal link
- Technique of building a fluid, three-dimensional vision by closing one's eyes, relying on words and feeling to avoid arbitrary graphical over-specification.
- Visual reasoning tasks often interleaved with intermediate visual states; promising direction in the field.
- Used to visually inspect separation of truth-related directions in model activation space across layers
- Publication series in which the work appeared.
- Used to visualize LLM true/false representations, revealing clear linear structure separating true from false statements
- Visualizing attention patterns weighted by the norm of value vectors to better show how much information is moved from each position
- Supervisory signals for visual outputs; functional tokens do not require it.