# Propositional Interpretability in Artificial Intelligence

arXiv: https://arxiv.org/abs/2501.15740 · HTML: https://mlsanity.com/paper/2501.15740/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 7 references that are in the map.
- First posted on arXiv 27 Jan 2025.

## Built on by (most cited first, 12 of 12)

- [The Impact of Off-Policy Training Data on Probe Generalisation](https://mlsanity.com/paper/2511.17408/) (2025)
- [A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i](https://mlsanity.com/paper/2505.00808/) (2025)
- [Mechanistic Interpretability Needs Philosophy](https://mlsanity.com/paper/2506.18852/) (2025)
- [LogicSkills: A Structured Benchmark for Formal Reasoning in Large Language Models](https://mlsanity.com/paper/2602.06533/) (2026)
- [Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii](https://mlsanity.com/paper/2505.01372/) (2025)
- [Are Sparse Autoencoders Useful for Java Function Bug Detection?](https://mlsanity.com/paper/2505.10375/) (2025)
- [Deflating Deflationism: A Critical Perspective on Debunking Arguments Against LLM Mentality](https://mlsanity.com/paper/2506.13403/) (2025)
- [A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents](https://mlsanity.com/paper/2602.08964/) (2026)
- [Radical AI Interpretability](https://mlsanity.com/paper/2606.26523/) (2026)
- [Explainability Through Systematicity: The Hard Systematicity Challenge for Artificial Intelligence](https://mlsanity.com/paper/2507.22197/) (2025)
- [Questionnaire Responses Do not Capture the Safety of AI Agents](https://mlsanity.com/paper/2603.14417/) (2026)
- [How LLMs Might Think](https://mlsanity.com/paper/2604.09674/) (2026)

## Abstract (arXiv)

Mechanistic interpretability is the program of explaining what AI systems are doing in terms of their internal mechanisms. I analyze some aspects of the program, along with setting out some concrete challenges and assessing progress to date. I argue for the importance of propositional interpretability, which involves interpreting a system's mechanisms and behavior in terms of propositional attitudes: attitudes (such as belief, desire, or subjective probability) to propositions (e.g. the proposition that it is hot outside). Propositional attitudes are the central way that we interpret and explain human beings and they are likely to be central in AI too. A central challenge is what I call thought logging: creating systems that log all of the relevant propositional attitudes in an AI system over time. I examine currently popular methods of interpretability (such as probing, sparse auto-encoders, and chain of thought methods) as well as philosophical methods of interpretation (including those grounded in psychosemantics) to assess their strengths and weaknesses as methods of propositional interpretability.