arXiv (OAI Expanded)
open access
Decoder-Preserving Sparse Autoencoders: Which Readouts Survive Sparse Compression?
Sparse autoencoders (SAEs) compress model activations into sparse codes, but equal reconstruction error and sparsity can preserve different linearly decodable signals. We formalize this ambiguity as a matrix-valued distortion between optimal ridge-prediction operators and train decoder-preserving SA
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation#1035632
- ReLATE: Accelerating Tensor Decomposition via Safe and Efficient Learning of Sparse Encodings#677415
- ReLATE: Accelerating Tensor Decomposition via Safe and Efficient Learning of Sparse Encodings#674218
- Comparison between Supervised and Unsupervised Learning in Deep Unfolded Sparse Signal Recovery#160946
- On the Interaction of Compressibility and Adversarial Robustness#1118405
Record · ID 1084296
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive