architecture · first seen 17 Oct 2026
JumpReLU
A sparse autoencoder activation function with learned per-feature thresholds that enables sparse, differentiable features.
Mentions per week
PapersCodeDiscussion
Earliest sources
- A Symmetry-Matching Approach to Blind-Spot Reduction in Sparse AutoencodersPapers · 17 Oct 2026 · Csaba Balogh
- Cross-Layer TopK: Dynamically Allocating Sparsity Across Layers in TranscodersPapers · 6 Nov 2026 · Anyuan Zhuo, Shaohua Zhang, Tianle Li, Yuan Lin, Diandian Gu, Jun Wang, Pinyan L…
Latest sources
- Cross-Layer TopK: Dynamically Allocating Sparsity Across Layers in TranscodersPapers · 6 Nov 2026 · Anyuan Zhuo, Shaohua Zhang, Tianle Li, Yuan Lin, Diandian Gu, Jun Wang, Pinyan L…
- A Symmetry-Matching Approach to Blind-Spot Reduction in Sparse AutoencodersPapers · 17 Oct 2026 · Csaba Balogh