Goodfire
@GoodfireAI
Using interpretability to understand, learn from, and design AI.
29 Following 22.8K Followers
Neural networks do math by rotating shapes.
We found a shape-rotating calculator hidden inside an LLM – and it’s used for more than just math! (1/6)
A simple example: days of the week, which lie on a circular path in models’ activations.
Steering linearly from Monday to Friday gets you incoherent outputs in between. Steering along the circular manifold means you cleanly shift from Mon → Tues → Wed → Thurs → Fri. (5/8)
Show more
Neural networks might speak English, but they think in shapes.
Understanding their rich *neural geometry* is key to understanding how they work – and to debugging and controlling them with precision.
Starting today, we’re releasing a series of posts on this research agenda. 🧵
Show more
