method
active
method:pca-of-mean-activations-and-probe-weightsPCA of mean activations and probe weights
Reveals low-dimensional counting manifolds.
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- PCA on 171 emotion probe activations across all tokens to produce ordered linear combinations and test if lower PCs are more persistent
- Statistical method used to analyze neural activity data.
- Used to test linear separability of group position.
- Used to reveal manifold geometry in Llama activations.
- Internals-based approach to which the logit monitor is complementary.
- PCA components treated as SAE latents for comparison.
- Hypothesis-generation tool for detecting distinct head behaviors via clustering.
- Limitations of PCA.