method
active
method:pca-projection-of-concept-activationsPCA projection of concept activations
Used to reveal manifold geometry in Llama activations.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Do Sparse Autoencoders Capture Concept Manifolds?citesmentions
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
- Reveals low-dimensional counting manifolds.
- Used to visually inspect separation of truth-related directions in model activation space across layers
- Statistical method used to analyze neural activity data.
- Used to visualize LLM true/false representations, revealing clear linear structure separating true from false statements
- Limitations of PCA.
- Technique of injecting steering vectors into model activations to test introspection and causal control of emotion vectors.
- Hypothesis-generation tool for detecting distinct head behaviors via clustering.