Differences

This shows you the differences between two versions of the page.

--- ml:nn_sparsity [2025/03/20 12:20] – [Sparse Autoencoders] jmflanig
+++ ml:nn_sparsity [2025/05/07 17:59] (current) – [Related Pages] jmflanig
@@ Line 5: / Line 5: @@
 ===== Papers =====
+  * [[https://arxiv.org/pdf/2102.04010|Zhou et al 2021 - Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch]]
-===== Sparse Autoencoders =====
-This section should maybe be moved into its own section, or moved to interpretability.
-  * [[https://arxiv.org/pdf/2309.08600|Cunningham et al 2023 - Sparse Autoencoders Find Highly Interpretable Features in Language Models]]
-  * [[https://transformer-circuits.pub/2023/monosemantic-features|2023 - Towards Monosemanticity: Decomposing Language Models With Dictionary Learning]]
-  * [[https://transformer-circuits.pub/2024/scaling-monosemanticity/index.html|2024 - Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet]]
 ===== Related Pages =====
   * [[Model Compression]]
   * [[Model Compression#Pruning & Sparsification]]
+  * [[mechanistic_interpretability#Sparse Autoencoders]]