Aaron Mueller
- Papers
- 8
Cite
Notes
Only stored in your browser.
Authored papers
8SAEs Are Good for Steering -- If You Select the Right Features
arXiv 2025
Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages
arXiv 2025
Position-aware Automatic Circuit Discovery
arXiv 2025
NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
arXiv 2024
Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
arXiv 2024
Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models
arXiv 2024
Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora
arXiv 2024
Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
arXiv 2024
Affiliations
Frequent co-authors
10from 8 papers