🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

I started Cypher last month after 8 years Ginkgo Bioworks working on the intersection of software and biology! At Cypher, I am building AI enabled software tools to supercharge scientists productivity and capabilities. Check this out! loom.com/share/2e18e219…

If you’ve ever - thought AI protein folding is magical ✨ - wanted more than a pLDDT score 🔎 - or just think mech interp in bio is cool 🤓 then read the 🧵 👇 on our first paper towards interpretable protein structure prediction just accepted to workshops at ICLR

🚀 Fellowship applications are OPEN for Encode: AI for Science. What if you could use AI to - Design shape-shifting robots - See through solid materials - Decode language of the brain - Create advanced materials

Learning to code will be like learning math: you’ll always use a calculator, but it teaches you how to think

Proud that this work was accepted at ICML as a spotlight poster! Reminder that you can just do things, especially in interpretability. Etowah Adams and I did most of this work in colab notebooks that cost a few dollars a month.

You can take a ESM's final-layer projection matrix (used to get logits) and apply it to intermediate layer embeddings. This can roughly tell you what the model “thinks” the sequence is at different layers. x.com/liambai21/stat…

Update to our ICML paper on interpreting features in protein language models: We ask human raters to assess the interpretability of SAE feature activations and ESM activations. Human raters found SAE features far more interpretable! x.com/etowah0/status…

MechInterp for pLMs has been considered a “dark art” for some time due to spurious correlations and pseudo-insights into biological mechanisms Happy to have contributed a bit to this ongoing effort, containing many stellar, honest results. Plenty of work yet to be done!