Consciousness
Hard problem, biological computationalism, care/SCI, non-dual teachers, Buddhism × AI institutional bridges.
Papers
91
+8
Thinkers
12
Frameworks
12
Methods
12
Claims
1,328
+201
Findings
1,057
+291
Hypotheses
280
Communities
12
New in this area (last 90d)
/recent ↗- Logits as a new monitor for evaluation awareness49d ago
- Understanding and Steering Llama 3 with Sparse Autoencoders - Goodfire49d ago
- Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context(2025)49d ago
- Features as Rewards: Scalable Supervision for Open-Ended Tasks via Interpretability(2026)49d ago
- Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal(2026)49d ago
- Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations(2026)49d ago
- Would this change your answer? Evaluating Explanations of LLM Behavior In The Wild with Counterfactual Experiments(2026)49d ago
- Verbalizable Representations Form a Global Workspace in Language Models49d ago
Cross-area bridges (15)
also-inEntities that appear in this area AND ≥1 other area. The conceptual seams — usually the most fruitful place to look for new essay material.
- conceptCognitive Light Cone
- frameworkActive Inference
- frameworkBasal Cognition
- frameworkFree Energy Principle
- frameworkTame Technological Approach To Mind Everywhere
- thinkerKyle Fish
- thinkerMichael Levin
- conceptBioelectricity
- conceptCausal Emergence
- conceptCollective Intelligence
- frameworkAttention Schema Theory
- frameworkAutopoiesis
- frameworkComputational Functionalism
- frameworkDiverse Intelligence
- frameworkGlobal workspace theory
Velocity movers (10)
new edges via area papersEntities whose connection to this area grew most in the window — new papers reinforcing existing thinkers / concepts / frameworks.
- thinkerEkdeep Singh Lubana+12
- thinkerThomas McGrath+12
- thinkerAtticus Geiger+12
- thinkerJack Merullo+10
- thinkerJack Lindsey+8
- thinkerOwen Lewis+8
- thinkerUsha Bhalla+8
- thinkerMichael Levin+8
- thinkerLeon Bergen+8
- thinkerNicholas Sofroniew+8
Top entities in Consciousness
Thinkers (12)
papersAuthors of area papers, by paper count
Frameworks (12)
linksFrameworks introduced or extended by area papers
- Basal Cognition10
- Tame Technological Approach To Mind Everywhere5
- Autopoiesis5
- Global workspace theory5
- Active Inference5
- Diverse Intelligence5
- Attention Schema Theory5
- Integrated Information Theory4
- Free Energy Principle4
- Computational Functionalism4
- Recurrent Processing Theory (RPT)4
- Five-Level Hierarchy of Functional Descriptions for Consciousness3
Methods (12)
linksMethods used in area papers
- Activation Steering6
- Logit Lens5
- Natural Language Autoencoders (NLAs)4
- Jacobian Lens3
- CHIVE (Counterfactual Hypothesis Investigation Via Edits)2
- Activation Difference Lens (ADL)2
- Consciousness Turing Test (c-TT)2
- Automated interpretability pipeline2
- Centered Kernel Alignment2
- Cascading Probe→Monitor pipeline2
- Activation Oracles (AO)2
- Activation injection at layer 1 residual stream2
Concepts (12)
linksConcepts referenced by area papers
Communities (12)
membersClusters with ≥2 area papers as members
- Mechanistic interpretability & model evaluation104
- Bioelectric morphogenesis & anatomical intelligence73
- Causal emergence in biological systems54
- Collective intelligence & distributed cognition48
- Design principles for care-centered systems44
- Alive AI interface ethics & design37
- Care as mechanism of intelligence29
- Relational self, care & aliveness28
- LLM introspective awareness of injected concepts25
- Mechanistic introspection in language models22
- Bioelectric morphogenesis & memory22
- Substrate-agnostic behavioral inference of cognition21
Top claims (10)
restatesClaims extracted from area papers, ranked by restate-degree
- All intelligence is collective intelligence: each of us consists of a huge number of cells working together to generate a coherent cognitive being with goals, preferences, and memories that belong to the whole and not to its parts.5
- All intelligences are collective intelligences — individual humans are collections of parts, competencies, drives, and tools both internal and external to the body.3
- All intelligences are collectives; individual intelligence arises from the interaction of many unintelligent components arranged in the right organisation.3
- Morphogenesis is a result of collective activity where cells cooperate toward a specific, invariant target morphology, exhibiting goal-directedness.3
- Morphogenesis is an instantiation of collective intelligence, exhibiting anatomical homeostasis and autonomous problem-solving in morphospace.3
- All intelligence is collective intelligence, in the sense that it is made of parts that must align with respect to system-level goals.2
- All intelligence is collective intelligence, in the sense that it is made of parts which must align with respect to system-level goals.2
- All intelligences are collectives and all individuals are collectives; individual and collective intelligence are not categorically distinct but unified by connectionist principles.2
- Morphogenesis is an autonomous process in geometry itself, arising from physical phenomena and geometric dynamics with relatively little dependence on genetic guidance.2
- Morphogenesis is the behavior of a collective intelligence of cells solving problems across multiple scales.2
Top findings (10)
restatesFindings extracted from area papers, ranked by restate-degree
- 17 of 83 tested emotions show significant association between self-eval transcript word mention and cosine similarity to emotion probe1
- 62% of emotions significantly elevated at 5 tokens after steering pulse ends1
- Across 5,568 judged conditions on four standard models from three architecture families, persona danger rankings under system prompting are preserved (rho=0.71-0.96) while activation-steering vulnerability diverges sharply.1
- Agentic self-evaluation emotionality correlates with SAE feature persistence: rho=+0.124, p=0.00011
- All intelligences are collective intelligences (higher-level selves composed of competent parts); implies distributed consciousness1
- Anatomical goal states could not be inferred from observation of stress states, revealing limits of external observer knowledge1
- Caterpillar memories survive metamorphosis into butterfly.1
- Correlation between self-evaluation and textual evaluation of SAE feature emotionality: rho=+0.051 (n.s.)1
- DAS trainable intervention finds sparser gender representations across layers compared to linear probe in Pythia-6.9B1
- 'Italian' is among the top five returned logits after parallel multi-source interchange intervention mixing language and Italy activations in GPT-20
Open questions (10)
Questions from area papers with no answers yet
- If we translate the Universality Hypothesis to the problem of consciousness, would it follow that an artificial system trained to perform the same tasks leading to consciousness formation in a human infant would exhibit consciousness as well?
- How do the molecular events brought on by injecting a frog's egg with an odorant molecule become expanded into a nervous system architecture which controls muscles to behaviorally seek out that odorant as an adult frog?
- What degree of concern and care should we exhibit toward the many diverse agents around us, and what criteria do we use to identify sentience, capacity for suffering, and other properties that have moral implications?
- Which of the indicator properties listed in Table 1 are displayed by existing AI systems, including frontier generative language or multimodal models, language agents, and deep reinforcement learning agents?
- Do human participants demonstrate the same insight dynamics predicted by active inference in the rule-learning paradigm (currently under investigation with eye tracking and crowd-sourced reaction times)?
- Could it be possible to create new forms of consciousness and kinds of minds, capable of experiencing, reflecting and understanding reality at a level far beyond current human communication patterns?
- Does self-referential processing causally instantiate algorithmic properties proposed by consciousness theories (recurrent integration, global broadcasting, metacognitive monitoring) in LLMs?
- Is a mutual nearest-neighbor alignment score of 0.16 indicative of strong alignment with remaining gap being noise, or does it signify poor alignment with major differences left to explain?
- Does self-referential prompting actually instantiate architectural recursion, global broadcasting, or recurrent integration at the algorithmic level as proposed by consciousness theories?
- If the minimization of free energy is just a corollary of descent onto a global random attractor, does this mean that adaptation and evolution are just ways of describing the same thing?
All papers in Consciousness
Status:
91 of 91