Author

Subhabrata Dutta

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects

FEGA is introduced, an unsupervised framework that removes the same active SAE feature across contexts and analyzes the resulting cloud of logit changes, showing that a feature can be interpretable and causally relevant without providing a stable direction for steering.

Phu Gia Hoang, Anwoy Chatterjee, Tanmoy Chakraborty et al. · arXiv.org · 0 citations

#natural language process... Preprint Aug 2026

MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines

Murano is an open source framework for designing, running, and reproducing mechanistic interpretability studies of large language models, intended for researchers across disciplines and builds on existing interpretability and machine learning libraries.

Alireza Bayat Makou, Emirhan Böge, Phu Gia Hoang et al. · 0 citations