method
active
method:umap-visualization-for-featuresUMAP visualization for features
Dimensionality reduction of SAE decoder vectors to create interactive feature maps.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- UMAP Embedding of Featuresrelated_to2D embedding of feature direction vectors used to visualize feature clusters and splitting geometry
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
- Used to visualize manifold locations.
- Used to visualize embedding clusters in two dimensions for qualitative assessment of convergence
- Synthesizing inputs maximizing component activation.
- Used to visualize LLM true/false representations, revealing clear linear structure separating true from false statements
- Premise that models represent concepts as features.
- Interpretable concept representations hypothesized as basic units of computation.
- Used to visually inspect separation of truth-related directions in model activation space across layers