Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Structural Inference: Interpreting Small Language Models with Susceptibilities
Garrett Baker, George Wang, Jesse Hoogland, Vinayak Pathak, Daniel Murfet
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| identify induction circuit via PC2 of per-token susceptibilities | 2-layer attention-only transformer · Pile subsets (per-token susceptibility PCA) | head loadings on PC2 | Improved |
| read PC3 of susceptibilities as bracket matching | 2-layer attention-only transformer · Pile subsets (per-token susceptibility PCA) | head loadings on PC3 | Mixed |
Closest papers by meaning
- Remarkable Robustness of LLMs: Stages of Inference? (NeurIPS 2025 · similarity 0.87)
- Distinguishing the Knowable from the Unknowable with Language Models (ICML 2024 · similarity 0.86)
- Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference (AAAI 2025 · similarity 0.86)
- Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention (AAAI 2024 · similarity 0.85)
- Statistical Hypothesis Testing for Auditing Robustness in Language Models (ICML 2025 · similarity 0.85)
- Towards Theoretical Understanding of Transformer Test-Time Computing: Investigation on In-Context Linear Regression (ICML 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
