Research — Reciprocal Research

Using mechanistic interpretability and computational neuroscience to study AI cognition and consciousness.

Research Program Studying what's happening inside Reciprocal Research exists to proactively build the empirical and conceptual tools the field needs. We use mechanistic interpretability, computational neuroscience, and psychometrics to study the internal dynamics of AI systems. Our work bridges biological and artificial cognition. Research Large Language Models Report Subjective Experience Under Self-Referential Processing Berg, de Lucena, Rosenblatt → Consciousness as Evaluation: Why Learning Requires Feeling AAAI 2026 Spring Symposium → The Pain Axis: LLMs Represent Self-Directed…

saved by

• Alima Deen

related reading

• Mechanistic Interpretability: A Challenge Common to Both Artificial and Biological Intelligencekempnerinstitute.harvard.edu
• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• Consciousness in Artificial Intelligencearxiv.org
• Transformer Circuits Threadtransformer-circuits.pub
• Tracing the thoughts of a large language model \ Anthropicanthropic.com
• Emergent introspective awareness in large language models \ Anthropicanthropic.com
• The Artificial Selftheartificialself.ai
• God Help Us, Let’s Try To Learn About Mechanistic Interpretability Techniquesastralcodexten.com
• A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
• 2311.08576arxiv.org
• Alignment of Complex Systems Research Group – ACS Research Programacsresearch.org
• 2310.01405arxiv.org