Skip to content

Author

Ai-Zhong Shen

1 paper 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.

#artificial intelligence Preprint Sep 2025

Mechanistic Interpretability with Sparse Autoencoder Neural Operators

The results show that moving from vector-valued to functional parameterizations, with concept and domain sparsity, extends SAEs from representing concept presence to modeling structured concept expression, highlighting the importance of parameterization.

Bahareh Tolooshams, Ai-Zhong Shen, Anima Anandkumar · 4 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.