method
active
method:principal-component-analysis-visualizationPrincipal Component Analysis Visualization
Used to visualize LLM true/false representations, revealing clear linear structure separating true from false statements
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- PCA Visualizationrelated_toUsed to visually inspect separation of truth-related directions in model activation space across layers
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.
- Linear-model solution that trades off with superposition.
- Statistical method used to analyze neural activity data.
- Method of optimizing input to cause a neuron to fire maximally, used to characterize what a neuron detects; establishes causal link
- Method used by Lu et al. to find orthogonal directions of maximum variance among 275 character archetypes in activation space
- Visualizes feature interference matrix.
- Primary visual evidence for linear truth representations in large LLMs
- Interactive tool for visualizing and inspecting learned binary logic circuits using modified DigitalJS library
- Visualizing attention patterns weighted by the norm of value vectors to better show how much information is moved from each position