2 citations · 7 across the 28 of their papers we have counts for
7 papers · 1 filter
MAxBench: A Multinomial Concept Recovery Benchmark
Divya Appapogu, Freya Behrens, Yonatan Belinkov +1
Fine-grained control of language model behaviors (e.g., steering) is among the more actionable outcomes of interpretability research. For binary concepts such as refusal, a single…
Between the Layers Lies the Truth: Uncertainty Estimation in LLMs Using Intra-Layer Local Information Scores
Zvi N. Badash, Yonatan Belinkov, Moti Freiman
Large language models (LLMs) are often confidently wrong, making reliable uncertainty estimation (UE) essential. Output-based heuristics are cheap but brittle, while probing intern…
Induction Meets Biology: Mechanisms of Repeat Detection in Protein Language Models
Gal Pomerants, Yaniv Nikankin, Anja Reusch +3
Protein sequences are abundant in repeating segments, both as exact copies and as approximate segments with mutations. These repeats are important for protein structure and functio…
Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks
Kevin Lu, Jannik Brinkmann, Stefan Huber +4
How do protein structure prediction models fold proteins? We investigate this question through causal interventions on the folding trunks of ESMFold, OpenFold, and Boltz-1. Across…
SAEs Are Good for Steering -- If You Select the Right Features
Dana Arad, Aaron Mueller, Yonatan Belinkov
Sparse Autoencoders (SAEs) have been proposed as an unsupervised approach to learn a decomposition of a model's latent space. This enables useful applications such as steering - in…
MIB: A Mechanistic Interpretability Benchmark
Aaron Mueller, Atticus Geiger, Sarah Wiegreffe +20
How can we know whether new mechanistic interpretability methods achieve real improvements? In pursuit of lasting evaluation standards, we propose MIB, a Mechanistic Interpretabili…
The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis
Aaron Mueller, Jannik Brinkmann, Millicent Li +10
Interpretability provides a toolset for understanding how and why neural networks behave in certain ways. However, there is little unity in the field: most studies employ ad-hoc ev…