4 citations · 17 across the 11 of their papers we have counts for
13 papers
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…
The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space
Jacob Brinton, Jannik Brinkmann, Mark Crovella +1
Large language models (LLMs) have recently demonstrated improved machine translation performance over strong supervised baselines. This raises questions as to what mechanisms under…
Pitfalls in Evaluating Interpretability Agents
Tal Haklay, Nikhil Prakash, Sana Pandey +5
Automated interpretability systems aim to reduce the need for human labor and scale analysis to increasingly large models and diverse tasks. Recent efforts toward this goal leverag…
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…
Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models
Dana Arad, Yonatan Belinkov, Hanjie Chen +5
Mechanistic interpretability (MI) seeks to uncover how language models (LMs) implement specific behaviors, yet measuring progress in MI remains challenging. The recently released M…
In-Context Learning Beyond Copying: A Training-Time Analysis of Abstractive ICL
Kerem Sahin, Sheridan Feucht, Adam Belfki +4
The sudden emergence of induction circuits and the ability to perform in-context copying in LLMs coincides with a sharp drop in training loss over a short span of the training proc…
CRISP: Persistent Concept Unlearning via Sparse Autoencoders
Tomer Ashuach, Dana Arad, Aaron Mueller +2
As large language models (LLMs) are increasingly deployed in real-world applications, the need to selectively remove unwanted knowledge while preserving model utility has become pa…
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…
Position-aware Automatic Circuit Discovery
Tal Haklay, Hadas Orgad, David Bau +2
A widely used strategy to discover and understand language model mechanisms is circuit analysis. A circuit is a minimal subgraph of a model's computation graph that executes a spec…
Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
Yaniv Nikankin, Anja Reusch, Aaron Mueller +1
Do large language models (LLMs) solve reasoning tasks by learning robust generalizable algorithms, or do they memorize training data? To investigate this question, we use arithmeti…
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…
NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
Jaden Fiotto-Kaufman, Alexander R. Loftus, Eric Todd +17
We introduce NNsight and NDIF, technologies that work in tandem to enable scientific study of the representations and computations learned by very large neural networks. NNsight is…
Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
Samuel Marks, Can Rager, Eric J. Michaud +3
We introduce methods for discovering and applying sparse feature circuits. These are causally implicated subnetworks of human-interpretable features for explaining language model b…