neural-geometry

Tag

Cards List
#neural-geometry

We removed an LM's ability to speak German (3 minute read)

TLDR AI · 2026-06-26 Cached

GoodfireAI releases a research agenda on understanding neural geometry in language models, demonstrating the ability to precisely control a model's capabilities, such as removing its ability to speak German.

0 favorites 0 likes
#neural-geometry

Can SAEs Capture Neural Geometry? (6 minute read)

TLDR AI · 2026-05-22 Cached

This article explores how sparse autoencoders (SAEs) can capture curved neural geometry, revealing three distinct ways SAE features represent manifolds, and presents an unsupervised pipeline to uncover geometric structure in neural representations.

0 favorites 0 likes
#neural-geometry

@FinanceYF5: Neural Networks Speak English, But They Think in "Shapes" 1/ Neural Networks Don't Think in Words They appear to speak English on the surface, but internally they may organize information in geometric space: curves, loops, surfaces, manifolds. Understanding neural geometry may be the key to understanding, debugging, and controlling models.

X AI KOLs Following · 2026-05-08 Cached

Neural networks appear to speak English on the surface, but internally organize information in geometric space (curves, loops, surfaces, manifolds). Understanding "neural geometry" may be the key to understanding, debugging, and controlling models.

0 favorites 0 likes
#neural-geometry

@GoodfireAI: Neural networks might speak English, but they think in shapes. Understanding their rich *neural geometry* is key to und…

X AI KOLs Timeline · 2026-05-07 Cached

Goodfire AI announces a new research agenda focused on neural geometry to improve the understanding, debugging, and control of neural networks.

0 favorites 0 likes
#neural-geometry

Three-Phase Transformer

Hugging Face Daily Papers · 2026-04-15 Cached

A research paper introducing Three-Phase Transformer (3PT), which applies Tesla's polyphase geometry to transformer architectures by organizing the residual stream into three 120° offset phases. The approach achieves 7.2% perplexity improvement on WikiText-103 with minimal parameters (0.00124% overhead) and 1.93× convergence speedup.

0 favorites 0 likes
← Back to home

Submit Feedback