Sparsity-reconstruction tradeoff

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

• VPD achieves better sparsity-reconstruction tradeoff than transcoders on 67M modelfinding0.743
  Empirical result demonstrating VPD's efficiency advantage in parameter decomposition.
• reconstruction accuracyconcept0.737
  Metric of how well models reconstruct information from hidden states; Sauers' study found showing janus thread extends distribution tails.
• Sauers' statistical anomaly: when models are given Janus post explaining transformers, reconstruction accuracy tails extend both ways, with ~1/1000 reconstructions anomalously accuratefinding0.716
  Statistically rigorous analysis of Claude introspection; suggests models may have latent introspective capabilities that can be enhanced or disrupted.
• Monotonic non-linearities are insufficient to reverse evolutionary outcomesclaim0.716
• Any system that persists must minimise surprisal, thereby gathering evidence for its own generative model.quote0.704
  Opening sentence defining self-evidencing.
• acting to optimize value and perception are two aspects of exactly the same principle; namely the minimisation of a quantity [free energy] that bounds the probability of sensory input, given a particular agent or phenotype.quote0.704
  Concise statement of the free-energy principle's unification of action and perception.
• Probing Complexity–Accuracy Trade-offconcept0.702
  Longstanding debate from probing literature about whether complex probes reveal genuine encodings or just memorise; this paper revives it for causal abstraction
• giving models janus's thread extends reconstruction accuracy distribution tails in both directionsfinding0.700
  Sauers' study: exposing models to janus's post extended both positive and negative extremes of reconstruction accuracy.