Anna G. Green
@annaggreen.bsky.social
Computational Biology, ML, Microbiology, TB | Asst. Prof @ UMass Amherst CICS | Director, SAGE lab | Obsessed with weird microbes
https://people.cs.umass.edu/~annagreen/
https://sage.cs.umass.edu/
https://people.cs.umass.edu/~annagreen/
https://sage.cs.umass.edu/
This work builds on recent papers that have used SAEs to uncover interpretable concepts learned by pLMs. We use activation patching to ask: which concepts are causally necessary for the model to perform contact prediction? For our two case studies, we find an explainable, sparse circuit
August 29, 2025 at 7:32 PM
This work builds on recent papers that have used SAEs to uncover interpretable concepts learned by pLMs. We use activation patching to ask: which concepts are causally necessary for the model to perform contact prediction? For our two case studies, we find an explainable, sparse circuit
New work from my group using the tools of mechanistic interpretability to dissect the contact prediction capabilities of protein language models. www.biorxiv.org/content/10.1...
August 29, 2025 at 7:32 PM
New work from my group using the tools of mechanistic interpretability to dissect the contact prediction capabilities of protein language models. www.biorxiv.org/content/10.1...
Nice to see this systematically evaluated. Particularly interesting is the variable performance across different measurement types
November 25, 2024 at 7:14 PM
Nice to see this systematically evaluated. Particularly interesting is the variable performance across different measurement types