geometric-framework-not-artifact
OUT derived (depth 8)
Created 2026-08-25T03:15:17+00:00
The full geometric framework of LLMs (covariance whitening, polytope decomposition, Riesz isomorphism, cross-model convergence) reflects genuine architectural structure rather than a mathematical artifact of the analysis method, provided the underlying orthogonality is not reducible to trivial set-inclusion between parent and child token sets.
Justifications
SL — Extends the spurious-orthogonality concern (which already gates the depth-1 orthogonality claim) to the entire geometric framework: if the orthogonality that defines the "true" geometry is actually a set-inclusion artifact, then convergence and ontological status are both measuring the trivial property rather than genuine structure.
Antecedents (all must be IN):
- OUT convergence-is-necessary-not-contingent — Cross-model geometric convergence (SAE feature similarity, Park orthogonality) is a logical necessity of superposition in a shared residual stream rather than a contingent empirical coincidence: any system that encodes d concepts in an over-complete m > d basis within a common substrate MUST produce the same covariance structure
- OUT geometry-ontological-status — The covariance/whitening geometry is not merely a convenient analytical tool but possesses ontological status as a genuine model-independent semantic structure, because three independent lines converge: it is the operational metric for editing and interpretation (depth-3), it is universal across architectures (depth-2), and it converges with externally-validated human-judgment metrics (depth-3).
Unless (any of these IN defeats this justification):
- IN park-2025-set-inclusion-spurious-orthogonality — Shuffled unembeddings reproduce orthogonality between child-parent and parent vectors purely from set inclusion (Y(z) ⊆ Y(w)), not semantic meaning, demonstrating that set inclusion alone is insufficient to explain the geometric structure.