I built a open source neural network shape validator [P]
Summary
An open source tool for validating the shapes of neural networks has been built and shared by the author.
Similar Articles
@GoodfireAI: Neural networks do math by rotating shapes. We found a shape-rotating calculator hidden inside an LLM – and it’s used f…
GoodfireAI found that neural networks perform math by rotating shapes, uncovering a shape-rotating calculator inside an LLM that is used for more than just math.
How Data Augmentation Shapes Neural Representations
This paper uses shape analysis tools to characterize how different data augmentation strategies reshape the geometry of neural network representations, finding that augmentation strength and type lead to distinct, well-behaved trajectories in shape space.
@GoodfireAI: Neural networks might speak English, but they think in shapes. Understanding their rich *neural geometry* is key to und…
Goodfire AI announces a new research agenda focused on neural geometry to improve the understanding, debugging, and control of neural networks.
Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks
Proposes a verification-based algorithm to compute provable bounds on exact SHAP values for neural networks, scaling to much larger search spaces than prior exact methods.
Show HN: Watch a neural net learn to play Snake
A web-based tool that visualizes a neural network (using PPO) learning to play Snake in real-time, with configurable parameters and 3D rendering.