method
active
method:maco-feature-visualizationMACO feature visualization
Used to visualize manifold locations.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- Feature Visualizationrelated_toMethod of optimizing input to cause a neuron to fire maximally, used to characterize what a neuron detects; establishes causal link
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.
- Dimensionality reduction of SAE decoder vectors to create interactive feature maps.
- Technique of building a fluid, three-dimensional vision by closing one's eyes, relying on words and feeling to avoid arbitrary graphical over-specification.
- Visualizes feature interference matrix.
- Used to visually inspect separation of truth-related directions in model activation space across layers
- Used to visualize LLM true/false representations, revealing clear linear structure separating true from false statements
- Method used with Andre and Anna: standing on site with eyes closed, abandoning preconceptions, visualizing the most comfortable remembered place
- Synthesizing inputs maximizing component activation.
- Visualizing attention patterns weighted by the norm of value vectors to better show how much information is moved from each position