finding
active
finding:fourier-components-explain-at-most-10-less-variance-than-an-equal-number-of-pca-componentsFourier components explain at most 10% less variance than an equal number of PCA components
Near-optimality of Fourier.
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Toy model.
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.
- PC1 explains 82% of variance in factor analysis of 2224 data points across 6 scoring dimensionsfinding0.761Dimensions are not independent; composite score is the reliable signal; six dimensions useful for understanding how not how much
- Higher-order modes.
- J-space component carries a median of only 6-7% of concept vector variance on Sonnet 4.5.finding0.752Small variance share.
- Hyperparameter tuning result for PCA; first principal component is optimal choice
- Fourier features with period 10 contribute to base-10 sum computation in the 28-neuron clusterfinding0.737One of the three base-10 Fourier periods identified in the sparse neuron set
- Mechanistic claim linking identified Fourier features to base-10 arithmetic
- Inverts the causal arrow: relationships produce individuality, not vice versa.
- Table 3.