Transformer Circuits Thread
A series of in-depth research publications from Anthropic's interpretability team reverse engineering how transformer language models actually work inside.
No account needed · sign in to keep your taste everywhere
More like this
Pages that share Transformer Circuits Thread's themes. Or browse all of Tech.
Google Research Blog
The official Google Research blog, with posts on machine learning, algorithms, quantum computing, health and science, la…
Windows on Theory
A research blog on the theory of computing, with essays and lecture notes on algorithms, complexity, cryptography, and l…
Academic Torrents
A distributed repository where researchers share enormous datasets, from machine learning corpora to video collections a…
BAIR Blog
The Berkeley Artificial Intelligence Research blog, where lab researchers explain their recent papers on robotics, visio…
VRAM Calculator
A calculator that estimates how much GPU memory a transformer-based model needs to run, based on model size, precision,…
When Machine Learning Tells the Wrong Story
A personal story of a research project on website-fingerprinting side channels, where a machine learning result turned o…
Stumble onto more like this
One click takes you to a page you didn't know you were looking for. Rate it and the next one lands closer to your taste.
Add to Browser — it's freeWorks in Chrome, Edge and Brave. No account needed.