method
active
method:pca-visualizationPCA Visualization
Used to visually inspect separation of truth-related directions in model activation space across layers
Neighborhood — ranked by edge-count
Methods (1)
method
- Used to visualize LLM true/false representations, revealing clear linear structure separating true from false statements
Claims (1)
claim
- Interpretation of weaker PCA separation and lower ASR in smaller models
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.
- 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
- PCA on 171 emotion probe activations across all tokens to produce ordered linear combinations and test if lower PCs are more persistent
- Justifies PCA choice over UMAP or t-SNE for the node-structured RN model.
- Primary visual evidence for linear truth representations in large LLMs
- Technique of building a fluid, three-dimensional vision by closing one's eyes, relying on words and feeling to avoid arbitrary graphical over-specification.
- Interactive tool for visualizing and inspecting learned binary logic circuits using modified DigitalJS library
- One of several applications of NCA cited to show breadth of the NCA framework