Identity Subspace of Left Equality model achieves ~0.50 IIA, indicating equality relations cannot be decomposed into input identities

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• The two-dimensional subspace reported by Burger et al. (2024) seems to reflect a stage of transition in the model's processing, rather than a universal property of truth directions.quote0.757
  Load-bearing interpretive claim about the layer-specificity of Burger et al.'s finding.
• Lexical entailment representation decomposes into word identity sub-representations with ~0.97-0.98 IIA (Lexeme Subspace of Lexical Entailment)finding0.750
  In contrast to hierarchical equality, lexical entailment in BERT decomposes into representations of word identities, not a single abstract relation.
• The discovery of perfect abstract equality representations that cannot be decomposed into entity representations is a foundational result informing our understanding of how symbolic and connectionist architectures coexistclaim0.735
  Concluding claim about theoretical significance of the hierarchical equality finding.
• Identity of first argument algorithm IIA consistently hovers around 50% for all alignment map types on hierarchical equality taskfinding0.730
  Exception to the general trend; attributed to insufficient RevNet capacity rather than algorithm not being implemented
• The two-dimensional subspace reported by Burger et al. reflects a transitional phase in model processing rather than a universal property of truth directions.claim0.726
  Reinterpretation of Burger et al.'s finding as layer-specific rather than universal.
• Linear alignment map ϕ_lin shows substantial IIA decrease in third layer for both equality relations and left equality relation algorithms in hierarchical equality taskfinding0.721
  Replicates Geiger et al. 2024b pattern of layer-dependent IIA degradation with linear maps
• The correlation between emotion subspace fraction and self-evaluated emotionality validates that emotion probe concepts somewhat overlap with the model's self-reported internal emotions.claim0.716
  Claim supporting the validity of the probe construction method via cross-validation with self-report
• Truth may be linearly separable in the model's representation space, but the structure is richer than a single linear axisclaim0.716
  Interpretive synthesis of DIM and cone intervention successes