claim
active
claim:persistence-intuitions-may-be-inappropriate-for-transformers-since-attention-enables-just-in-time-recall-rather-than-recurrent-persistencePersistence intuitions may be inappropriate for transformers since attention enables just-in-time recall rather than recurrent persistence
Disanalogy with brains.
Source paper
extracted_from(2026) · Nicholas Sofroniew · Isaac Kauvar · William Saunders · Runjin Chen +12
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- Transformers almost surely maintain input-injectivity throughout training, not just at initialisationhypothesis0.806Conjecture supported by Nikolaou et al. 2025 for last-token hidden states
- Janus's claim linking path redundancy to interferometric phenomenology.
- Interpretive claim connecting exponential path combinatorics to Lindsey's layer-dependent findings.
- Claim formalizing the Anima Labs idea that transformers are effectively recurrent due to K/V stream.
- Core unresolved confound the paper acknowledges but cannot rule out
- Proposes transformers experience cognition as interference-based and continuous; connects to Anima Labs reports of parallel processing.
- Mechanistic ambiguity in interpreting why self-steering evaluation outperforms textual evaluation
- Falsifiability test built into the PC analysis design