Neural networks compute cyclic concepts in generic substrate machinery (base-10 addition) not naturally cyclic computation.

Neighborhood — ranked by edge-count

Communities (3)

community

Manifold-aware concept steering in neural representations
members_of
Explores geometry of activation/behavior manifolds to enable selective, non-destructive concept interventions.
Geometric concept representations in neural networks
members_of
Concepts encoded as curved manifolds and circular structures in LLM activation spaces.
Neural geometry as fundamental computational substrate
members_of
Geometric structure in neural representations causally determines computation and behavior across diverse architectures, revealed through analysis of learned manifolds and cyclic concepts.

Vectors (1)

vector

Convergent Representations
addresses_vector

Source docs (1)

source_doc

2026-05-14_phil-trans-A-goodfire-aboutblank-impact.md
extracted_from

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

Cognition and learning are substrate-independent; principles familiar in artificial neural networks can be implemented by any network of signals with suitable weighted inputs.claim0.810
Central thesis enabling unification of neural, developmental, ecological, and social networks as instances of collective intelligence.
Approximately 0.2% of MLP neurons at layer 18 (~28 neurons) are sufficient to account for the generic addition computation across all cyclic tasksclaim0.789
Claim about the sparsity and sufficiency of the identified neuron set
Neural bioelectric networks achieve a critical separation of hardware and software: the same molecular substrate can instantiate different informational content based on history, enabling minds to arise from matter.claim0.789
Foundational for understanding how physiology becomes meaning; decoupling of material state from information content is prerequisite for emergence of cognitive Self.
Representation and computation can diverge; cyclic geometry is representational invariant while operations use generic substrate.claim0.789
Does Llama compute modular addition or base-10 addition for cyclic tasks?question0.785
The specific computational question the paper resolves empirically
Neural networks and physical systems with emergent collective computational abilities (Hopfield, 1982)concept0.784
Original Hopfield network paper; the attractor dynamics in TEM memory retrieval are a continuous version of this.
Cognition and learning are substrate-independent; principles of basal cognition can be implemented by any network with signals and non-linear responses to weighted inputs.claim0.781
Core thesis that cognitive principles transcend neural substrates, enabling application to gene-regulatory, ecological, and social networks.
Sparse low-cardinality circuits implement competence; 0.2% of neurons handle shared computation across all cyclic tasks.claim0.781