hypothesis

active

hypothesis:we-hypothesize-that-a-representation-network-rn-emerges-from-llm-representations-where-each-dimension-is-a-node-and-latent-connections-exist-between-nodes-or-clusters-of-nodes

We hypothesize that a Representation Network (RN) emerges from LLM representations, where each dimension is a node and latent connections exist between nodes or clusters of nodes.

Core methodological hypothesis enabling the application of IIT to LLM representation sequences.

Source paper

extracted_from

Can "consciousness" be observed from large language model (LLM) internal states? Dissecting LLM representations obtained from Theory of Mind test with Integrated Information Theory and Span Representation analysis

(2025) · Li, Jingkai

Neighborhood — ranked by edge-count

Concepts (1)

concept

Can 'Consciousness' Be Observed from Large Language Model (LLM) Internal States? Dissecting LLM Representations Obtained from Theory of Mind Test with Integrated Information Theory and Span Representation Analysis
introduces
The primary paper being extracted — applies IIT 3.0 and 4.0 to LLM representation sequences derived from ToM test data to investigate whether consciousness phenomena can be observed.

Frameworks (1)

framework

Representation Network (RN)
grounds
Novel construct introduced by this paper: a hypothetical graph embedded in the time series of LLM representations, where each dimension is a node and latent connections are edges.

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.

"Representation geometry is a window into the inner world of neural networks."quote0.817
The paper's concluding summary statement asserting the deep interpretive significance of representation geometry.
The geometry of internal representations and the geometry of model behavior share a precise correspondence — representation geometry is a window into the inner world of neural networks.claim0.815
The paper's deepest interpretive claim, asserting that representation structure and behavioral structure are not coincidentally aligned but deeply connected.
What is the relationship between different dimensions or clusters of dimensions in LLM representations? Do they and/or how do they interact with each other?question0.811
Motivates the RN hypothesis by pointing to the unknown relational structure within high-dimensional representation vectors.
Deep representations have a special significance in recurrent networks, allowing coordinated behaviour without losing sensitivity to new inputs.claim0.808
Importance of hierarchical structure for flexible coordination.
The LLM itself cannot 'experience' what it generates and therefore cannot possess consciousness; the RN is a higher-level construct that is independent of the LLM's architecture once representations are generated.claim0.807
Key theoretical position distinguishing analysis of representations from analysis of LLM architecture.
Neural networks, trained with different objectives on different data and modalities, are converging to a shared statistical model of reality in their representation spaces.quote0.789
The paper's central thesis statement, presented prominently after the abstract
LLM representations exhibit intriguing patterns under spatio-permutational analyses, suggesting a potentially profound yet tentative indication of consciousness.claim0.787
Qualified positive claim from spatio permutation analysis where two cases satisfy all three criteria.
Linear representation hypothesis: neural networks represent meaningful concepts as directions in their activation spaces.hypothesis0.786
Foundation for interpreting features as linear directions.