arXiv cs.AI6h agoenergy 98

Scaling Laws for SAE Training Data

Abstract page for arXiv paper 2611.07756: Scaling Laws for SAE Training Data

read the original at arXiv cs.AI →
This source publishes only a summary in its feed, so the full article lives at the outlet. The link above and below goes to the original.

more from the stream

Teach the Way It Thinks: Guiding LLM Post-training Data Engineering with Sparse Autoencoders (arXiv cs.AI) Multi-step SWE: Can Coding Agents Keep Building on Their Own Code Over Long Horizons? (arXiv cs.AI) When Attribution Patching Lies: Diagnosis and a Second-Order Correction (arXiv cs.AI) ← back to upsy.si