A First Step Towards Interpretable Protein Structure Prediction
With SAEFold, we enable mechanistic interpretability on ESMFold, a protein structure prediction model, for the first time.
Watch @NithinParsan demo a case study here w/ links for paper & open-source code ๐
A First Step Towards Interpretable Protein Structure Prediction
With SAEFold, we enable mechanistic interpretability on ESMFold, a protein structure prediction model, for the first time.
Watch @NithinParsan demo a case study here w/ links for paper & open-source code ๐
If youโve ever
- thought AI protein folding is magical โจ
- wanted more than a pLDDT score ๐
- or just think mech interp in bio is cool ๐ค
then read the ๐งตย ๐ on our first paper towards interpretable protein structure prediction just accepted to workshops at ICLR
For anyone going to ICLR, we'll be presenting our poster at the GEM, LMRL, SciFM, XAI4Science, and MLMP workshops. Stop by if you're curious about bio interp!
shoutout @liambai21 and @etowah0 for beating us to the punch on translating mech interp to protein language models. excited to see where these techniques will lead given the dense amt of coevolutionary structure info learned by these models.
Incredibly excited to launch publicly as part of @ycombinator's Fall 2024 Batch. Send us a DM if you're in the interpretability space or working in biotech. @johnyang100 and @NithinParsan