Methods › Computer Vision › Generative Models › k-Sparse Autoencoder
k-Sparse Autoencoder
Introduced by Alireza Makhzani et al. in k-Sparse Autoencoders
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
k-Sparse Autoencoders are autoencoders with linear activation function, where in hidden layers only the k highest activities are kept. This achieves exact sparsity in the hidden representation. Backpropagation only goes through the the top k activated units. This can be achieved with a ReLU layer with an adjustable threshold.
Papers archive 2025-07-28
3 shown of 3, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability 26 Mar 2025 · 1 repository · arXiv:2503.20483Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
-
PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders 14 Mar 2025 · 0 repositories · arXiv:2503.11232
-
k-Sparse Autoencoders 19 Dec 2013 · 3 repositories · arXiv:1312.5663
Tasks archive 2025-07-28
10 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections