method
active
method:pca-baselinePCA Baseline
PCA components treated as SAE latents for comparison.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- SAEBenchusesEvaluation suite of eight metrics across four capabilities.
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.
- Linear-model solution that trades off with superposition.
- Used to visually inspect separation of truth-related directions in model activation space across layers
- Reveals low-dimensional counting manifolds.
- Limitations of PCA.
- PCA on 171 emotion probe activations across all tokens to produce ordered linear combinations and test if lower PCs are more persistent
- Conditional generation on explicit Big Five labels using per-dimension descriptors; used as inference-time baseline
- Used to test linear separability of group position.