# Unveiling Latent Knowledge in Chemistry Language Models through Sparse Autoencoders

arXiv: https://arxiv.org/abs/2512.08077 · HTML: https://mlsanity.com/paper/2512.08077/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Interpreting biomedical and science models, one of 13 directions in Mechanistic interpretability.
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 8 Dec 2025.

## Placed in

- Mechanistic interpretability / [Interpreting biomedical and science models](https://mlsanity.com/mechinterp/interpreting-biomedical-and-science-models/)

## Builds on (most cited first, 9 of 9)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2](https://mlsanity.com/paper/2408.05147/) (2024)
- [Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models](https://mlsanity.com/paper/1811.12823/) (2018)
- [A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders](https://mlsanity.com/paper/2409.14507/) (2024)
- [Learning Multi-Level Features with Matryoshka Sparse Autoencoders](https://mlsanity.com/paper/2503.17547/) (2025)
- [InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders](https://mlsanity.com/paper/2412.12101/) (2024)
- [Towards Interpretable Protein Structure Prediction with Sparse Autoencoders](https://mlsanity.com/paper/2503.08764/) (2025)

## Built on by (most cited first, 2 of 2)

- [What Does a Chemical Language Model Know About Molecules?](https://mlsanity.com/paper/2606.23443/) (2026)
- [SMolLM: Small Language Models Learn Small Molecular Grammar](https://mlsanity.com/paper/2605.06322/) (2026)

## Abstract (arXiv)

Since the advent of machine learning, interpretability has remained a persistent challenge, becoming increasingly urgent as generative models support high-stakes applications in drug and material discovery. Recent advances in large language model (LLM) architectures have yielded chemistry language models (CLMs) with impressive capabilities in molecular property prediction and molecular generation. However, how these models internally represent chemical knowledge remains poorly understood. In this work, we extend sparse autoencoder techniques to uncover and examine interpretable features within CLMs. Applying our methodology to the Foundation Models for Materials (FM4M) SMI-TED chemistry foundation model, we extract semantically meaningful latent features and analyse their activation patterns across diverse molecular datasets. Our findings reveal that these models encode a rich landscape of chemical concepts. We identify correlations between specific latent features and distinct domains of chemical knowledge, including structural motifs, physicochemical properties, and pharmacological drug classes. Our approach provides a generalisable framework for uncovering latent knowledge in chemistry-focused AI systems. This work has implications for both foundational understanding and practical deployment; with the potential to accelerate computational chemistry research.