Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy (2025.emnlp-main)
Copied to clipboard
Nikita Balagansky, Yaroslav Aksenov, Daniil Laptev, Vadim Kurochkin, Gleb Gerasimov, Nikita Koriagin, Daniil Gavrilov
| Challenge: | Sparse Autoencoders (SAEs) are powerful tools for interpreting neural networks . conventional SAEs are constrained by the fixed sparsity level chosen during training . |
| Approach: | They propose a training objective that trains a single SAE to optimise reconstructions across multiple sparsity levels simultaneously. |
| Outcome: | The proposed objective achieves Pareto-optimal trade-offs between sparsity and explained variance, outperforming traditional SAEs trained at individual sparsities. |
Similar Papers
On the Versatility of Sparse Autoencoders for In-Context Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Sparse autoencoders (SAEs) are emerging as a key analytical tool in interpretability for large language models. |
| Approach: | They propose to use SAEs to extract knowledge from billions of tokens for sparse reconstruction. |
| Outcome: | The proposed model can extract knowledge from billions of tokens for sparse reconstruction. |
AdaptiveK: Complexity-Driven Sparse Autoencoders for Interpretable Language Model Representations (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to decomposing model activations into interpretable features fail to account for input complexity. |
| Approach: | They propose a framework that dynamically adjusts sparsity levels based on the semantic complexity of each input. |
| Outcome: | The proposed framework outperforms fixed-sparsity approaches on reconstruction fidelity, explained variance, cosine similarity and interpretability metrics while eliminating the burden of extensive hyperparameter tuning. |
Sparse Autoencoder Features for Classifications and Transferability (2025.emnlp-main)
Copied to clipboard
| Challenge: | Sparse Autoencoders (SAEs) provide potential for uncovering structured, human-interpretable representations in Large Language Models (LLMs). |
| Approach: | They analyze SAEs for interpretable feature extraction from Large Language Models in safety-critical classification tasks. |
| Outcome: | The proposed framework outperforms hidden-state and BoW models while demonstrating cross-lingual toxicity detection and visual classification tasks. |
AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders (2026.eacl-long)
Copied to clipboard
Georgii Aparin, Tasnima Sadekova, Alexey Rukhovich, Assel Yermekova, Laida Kushnareva, Vadim Popov, Kristian Kuznetsov, Irina Piontkovskaya
| Challenge: | Feature steering reduces Whisper’s false speech detections by 70% with negligible WER increase, demonstrating real-world applicability. |
| Approach: | They train Sparse Autoencoders across all encoder layers of Whisper and HuBERT and evaluate their stability, interpretability, and practical utility. |
| Outcome: | The proposed models capture general acoustic and semantic information as well as specific events, including environmental noises and paralinguistic sounds, and disentangle them effectively. |
Group-SAE: Efficient Training of Sparse Autoencoders for Large Language Models via Layer Groups (2025.emnlp-main)
Copied to clipboard
| Challenge: | Sparse Autoencoders (SAEs) are a promising unsupervised approach for understanding the representations of layers of Large Language Models (LLMs). |
| Approach: | They propose a method that groups similar models and trains a single SAE per group based on representational similarity across layers. |
| Outcome: | Experiments on Pythia family models show that the proposed method significantly accelerates training with minimal impact on reconstruction quality and comparable downstream task performance and interpretability over baseline SAEs trained layer by layer. |
Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning (2025.findings-naacl)
Copied to clipboard
| Challenge: | Sparse Autoencoders (SAEs) are a promising approach for extracting neural network representations by learning a sparse and overcomplete decomposition of the network’s internal activations. |
| Approach: | They propose a method that learns a sparse and overcomplete decomposition of the network's internal activations and a gradient approach to learn latents. |
| Outcome: | The proposed algorithms improve the performance of the k-sparse autoencoder and the ability to learn latent features. |
Route Sparse Autoencoder to Interpret Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Sparse autoencoders (SAEs) extract interpretable and monosemantic features in large language models . prior work focused on feature extraction from a single layer, failing to capture activations that span multiple layers. |
| Approach: | They propose a framework that integrates a routing mechanism with a shared SAE to efficiently extract features from multiple layers. |
| Outcome: | The proposed framework extracts features from multiple layers while incurring minimal parameter overhead while achieving high interpretability and flexibility. |
Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models (2025.findings-naacl)
Copied to clipboard
| Challenge: | Sparse Autoencoders (SAEs) are a promising tool for disentangling FM representations, but they struggle to capture rare, yet crucial concepts in the data. |
| Approach: | They propose a technique to train Sparse Autoencoders to illuminate elusive dark matter features by focusing on specific subdomains. |
| Outcome: | The proposed method achieves 12.5% better classification accuracy than general-purpose SAEs when applied to remove spurious gender information. |
Evaluating Sparse Autoencoders for Monosemantic Representation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Sparse autoencoders (SAEs) have been proposed to mitigate polysemanticity, where neurons activate for multiple unrelated concepts. |
| Approach: | They propose a sparse autoencoder to transform dense activations into sparser, more interpretable features by transforming them into sparses. |
| Outcome: | The proposed model reduces polysemanticity and achieves higher concept separability. |
Mechanistic Interpretability Should Prioritize Feature Consistency in Sparse Autoencoders (2026.acl-long)
Copied to clipboard
Xiangchen Song, Aashiq Muhamed, Yujia Zheng, Lingjing Kong, Zeyu Tang, Mona T. Diab, Virginia Smith, Kun Zhang
| Challenge: | Sparse Autoencoders (SAEs) are a tool in mechanistic interpretability (MI) but the aspiration to identify a canonical set of features is challenged by the observed inconsistency of learned SAE features across different training runs. |
| Approach: | They propose to use the Pairwise Dictionary Mean Correlation Coefficient to quantify SAE feature consistency as an evaluation axis alongside reconstruction and sparsity. |
| Outcome: | The proposed measure is based on the pairwise dictionary mean correlation coefficient (PW-MCC) on LLM activations. |