concept
active
concept:latent-space-representationsLatent-Space Representations
Substrate on which causal emergence was computed across agent lifetimes; aligned with learning success.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Transformer decoder architectureassociated_withBase architecture of reasoning LLMs studied, with attention and MLP blocks per layer
Concepts (3)
concept
- Causal Emergenceassociated_withCore concept: degree to which an agent exerts unique predictive power on its future; key to cognition at all scales.
- Recently proposed method for estimating causal emergence; applied to RL agent latent-space representations.
- Reflection directionassociated_withA direction in the model's representation space that governs self-reflection behavior, computed as mean difference between reflection and non-reflection embeddings
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.
- The central question of whether representational geometry implies corresponding computational structure
- Representations of one's own mental states; associated with consciousness in higher-order theories.
- Hidden or underdeveloped structures existing 'between the lines' of a configuration that can be enhanced and developed through harmony-seeking computation.
- Hierarchical representations in neural networks that allow compression and coordinated behaviour while retaining sensitivity to input changes.
- Statistical regularities stored in pretrained models.
- First of three core numbered hypotheses in the abstract defining the framework's ontology.
- Foundational methodological claim enabling a research program rather than mysterianism.
- Reasoning approach using learnable hidden embeddings.