{"url":"/method/k-sparse-autoencoder","slug":"k-sparse-autoencoder","name":"k-Sparse Autoencoder","full_name":"k-Sparse Autoencoder","full_name_withheld":false,"description_markdown":"**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](https://paperswithcode.com/method/relu) layer with an adjustable threshold.","description_state":"present","introduced_year":null,"introduced_by":{"title":"k-Sparse Autoencoders","paper":"/paper/k-sparse-autoencoders","first_author":"Alireza Makhzani","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/k-sparse-autoencoders"},"source":{"url":"http://arxiv.org/abs/1312.5663v2","title":"k-Sparse Autoencoders","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/snooky23/K-Sparse-AutoEncoder","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Models","url":"/methods/category/generative-models","pwc_aliases":[]}],"n_papers_tagged":3,"archive_num_papers":3,"papers_newest_first":[{"paper":"/paper/dissecting-and-mitigating-diffusion-bias-via","title":"Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability","date":"2025-03-26","arxiv_id":"2503.20483","n_code_links":1,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":1}},{"paper":null,"title":"PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders","date":"2025-03-14","arxiv_id":"2503.11232","n_code_links":0,"syntology":null},{"paper":"/paper/k-sparse-autoencoders","title":"k-Sparse Autoencoders","date":"2013-12-19","arxiv_id":"1312.5663","n_code_links":3,"syntology":null}],"papers_shown":3,"tasks":[{"task":"/task/age-unbiased","name":"Age/Unbiased","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/decision-making","name":"Decision Making","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/image-generation","name":"Image Generation","papers":1},{"task":"/task/interpretability-techniques-for-deep-learning","name":"Interpretability Techniques for Deep Learning","papers":1},{"task":"/task/memorization","name":"Memorization","papers":1},{"task":"/task/privacy-preserving","name":"Privacy Preserving","papers":1},{"task":"/task/race-unbiased","name":"Race/Unbiased","papers":1}],"tasks_shown":10,"n_tasks":10,"usage_by_year":[{"year":"2013","papers":1},{"year":"2025","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/k-sparse-autoencoder"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}