SPAR Research Library
A collection of 145 research reports from the Supervised Program for Alignment Research (SPAR), covering AI safety, AI policy, interpretability, and more.
Isha Harris Mentored by Gary Abel Biological AI models are powerful tools for detecting biological threats, but it remains unclear whether their predictions generalize to highly non-natural proteins. This is increasingly important as AI-enabled biodesign produces novel sequences that may not be reliably captured by direct sequence-comparison approaches used in DNA synthesis screening. Here, we use sparse autoencoder (SAE) features from protein language model activations to test whether interpretable internal representations can identify structural similarity across generated proteins. We…
saved by
related reading
- Automated Weak-to-Strong Researcheralignment.anthropic.com
- A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Modelsarxiv.org
- Sparse Autoencoders Find Highly Interpretable Features in Language Modelsarxiv.org
- Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropicanthropic.com
- Spring 2026 Projects - SPARsparai.org
- Surfacing Pathological Behaviors in Language Models | Transluce AItransluce.org
- Sparse Autoencoders Reveal Universal Feature Spaces Across Large Language Modelsarxiv.org
- [2604.16812] Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org
- Auditing language models for hidden objectives — LessWronglesswrong.com
- Student Projects - CS 2881R AI Safetyboazbk.github.io
- Towards the explainability of protein language modelsnature.com
- AI Safety | Arkosevictoriabrook.github.io