Study Examines How Activation-Cache Compression Affects Sparse Autoencoder Training
A new arXiv paper investigates the effects of compressing the large caches of model activations required to train sparse autoencoders, examining impacts on the resulting SAEs.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-09 05:00 · arXiv cs.LG
How Small Can We Go? Calibrating Activation-Cache Compression for SAE Training