covariance-geometry-unifies-analysis-and-editing

OUT derived (depth 2)

Created 2026-08-25T03:02:14+00:00 · Reviewed 2026-08-25T04:28:09+00:00

The mathematically principled framework for both interpreting (SAE feature extraction, Park polytope analysis) and modifying (ROME rank-one edits) LLM representations is second-moment covariance geometry applied to the residual stream, since C = KKᵀ whitening defines the canonical coordinate system in which all three operations become linear algebra on the same substrate.

Justifications

SL — The universality of the residual-stream substrate provides the *where*; the covariance-geometry canonical tool provides the *how*. Neither suffices alone: without universality the geometry is model-specific; without the canonical tool the substrate has no principled coordinate system. Their conjunction yields a unified algebraic framework.

Antecedents (all must be IN):

  • OUT residual-stream-universal-substrate — SAE (middle-layer residual stream), ROME (mid-layer MLP value projection), and Park (final-layer unembedding) all identify the residual stream at different depths as the primary locus of interpretable geometric structure.
  • IN covariance-geometry-as-canonical-tool — Independent lines of work (ROME's key-space projection and Park's unembedding whitening) converge on using empirical second-moment matrices to define the "correct" inner product for reasoning about transformer representations.

Dependents

These beliefs depend on this one: