Introspection or entropy? Re-examining concept-injection “introspection” in open models — LessWrong

Thanks to Joshua Joseph, Dillon Plunkett, and Julian Huang for their feedback and for helping me refine these ideas. …

x Introspection or entropy? Re-examining concept-injection “introspection” in open models — LessWrong Interpretability (ML & AI) Introspection Philosophy Transformers AI Frontpage 62 Introspection or entropy? Re-examining concept-injection “introspection” in open models by agastyasridharan 25th Jun 2026 17 min read 4 62 Thanks to Joshua Joseph, Dillon Plunkett, and Julian Huang for their feedback and for helping me refine these ideas. Anthropic recently reported that language models can “introspect.” They take a steering vector for a concept like “oceans,” add it into the model’s internal acti

related reading

• Emergent introspective awareness in large language models \ Anthropicanthropic.com
• Small Models Can Introspect, Toovgel.me
• Emergent Introspective Awareness in Large Language Modelstransformer-circuits.pub
• Emergent Introspective Awareness in Large Language Modelstransformer-circuits.pub
• Emergent Introspection in AI is Content-Agnosticarxiv.org
• [2602.20031] Latent Introspection: Models Can Detect Prior Concept Injectionsarxiv.org
• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• Tracing the thoughts of a large language model \ Anthropicanthropic.com
• A global workspace in language models \ Anthropicanthropic.com
• [2508.14802] Privileged Self-Access Matters for Introspection in AIarxiv.org
• [2607.14111] Introspection Fine-Tuning (IFT): Training Small LLMs to Introspectarxiv.org
• interpreting GPT: the logit lens — LessWronglesswrong.com