Cover Image

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Balagansky, Nikita, Aksenov, Yaroslav, Laptev, Daniil, Kurochkin, Vadim, Gerasimov, Gleb, Koryagin, Nikita, Gavrilov, Daniil
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders
by: Kurochkin, Vadim, et al.
Published: (2025)

Teach Old SAEs New Domain Tricks with Boosting
by: Koriagin, Nikita, et al.
Published: (2025)

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
by: Laptev, Daniil, et al.
Published: (2025)

Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors
by: Sinii, Viacheslav, et al.
Published: (2025)

You Do Not Fully Utilize Transformer's Representation Capacity
by: Gerasimov, Gleb, et al.
Published: (2025)

Next Embedding Prediction Makes World Models Stronger
by: Bredis, George, et al.
Published: (2026)

Mechanistic Permutability: Match Features Across Layers
by: Balagansky, Nikita, et al.
Published: (2024)

Trust-Region Behavior Blending for On-Policy Distillation
by: Plyusov, Daniil, et al.
Published: (2026)

Steering LLM Reasoning Through Bias-Only Adaptation
by: Sinii, Viacheslav, et al.
Published: (2025)

Learn Your Reference Model for Real Good Alignment
by: Gorbatovski, Alexey, et al.
Published: (2024)

Linear Transformers with Learnable Kernel Functions are Better In-Context Models
by: Aksenov, Yaroslav, et al.
Published: (2024)

Diffusion Language Models Generation Can Be Halted Early
by: Vaina, Sofia Maria Lo Cicero, et al.
Published: (2023)

Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success
by: Bredis, George, et al.
Published: (2025)

Learning Shortest Paths with Generative Flow Networks
by: Morozov, Nikita, et al.
Published: (2026)

F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
by: Plyusov, Daniil, et al.
Published: (2026)

Improving GFlowNets with Monte Carlo Tree Search
by: Morozov, Nikita, et al.
Published: (2024)

Joint Training Across Multiple Activation Sparsity Regimes
by: Wang, Haotian
Published: (2026)

Benchmarking Concept-Spilling Across Languages in LLMs
by: Badanin, Ilia, et al.
Published: (2026)

Sparse Autoencoders for Sequential Recommendation Models: Interpretation and Flexible Control
by: Klenitskiy, Anton, et al.
Published: (2025)

UPath: Universal Planner Across Topological Heterogeneity For Grid-Based Pathfinding
by: Ananikian, Aleksandr, et al.
Published: (2026)

A New Perspective on Transformers in Online Reinforcement Learning for Continuous Control
by: Kachaev, Nikita, et al.
Published: (2025)

Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization
by: Kachaev, Nikita, et al.
Published: (2025)

Performance Insights-based AI-driven Football Transfer Fee Prediction
by: Sulimov, Daniil
Published: (2024)

Guided Star-Shaped Masked Diffusion
by: Meshchaninov, Viacheslav, et al.
Published: (2025)

XShare: Collaborative in-Batch Expert Sharing for Faster MoE Inference
by: Vankov, Daniil, et al.
Published: (2026)

Extreme Model Compression with Structured Sparsity at Low Precision
by: Liu, Dan, et al.
Published: (2025)

Universal time-series forecasting with mixture predictors
by: Ryabko, Daniil
Published: (2020)

Facilitating large language model Russian adaptation with Learned Embedding Propagation
by: Tikhomirov, Mikhail, et al.
Published: (2024)

Contrastive Sparse Autoencoders for Interpreting Planning of Chess-Playing Agents
by: Poupart, Yoann
Published: (2024)

Hierarchical AI-Meteorologist: LLM-Agent System for Multi-Scale and Explainable Weather Forecast Reporting
by: Sukhorukov, Daniil, et al.
Published: (2025)

Post-Training Sparse Attention with Double Sparsity
by: Yang, Shuo, et al.
Published: (2024)

Mechanistic Interpretability with Sparse Autoencoder Neural Operators
by: Tolooshams, Bahareh, et al.
Published: (2025)

Causal Interpretation of Sparse Autoencoder Features in Vision
by: Han, Sangyu, et al.
Published: (2025)

IGANN Sparse: Bridging Sparsity and Interpretability with Non-linear Insight
by: Stoecker, Theodor, et al.
Published: (2024)

Neural network task specialization via domain constraining
by: Malashin, Roman, et al.
Published: (2025)

Interpreting CLIP with Hierarchical Sparse Autoencoders
by: Zaigrajew, Vladimir, et al.
Published: (2025)

Prompt-Efficient Fine-Tuning for GPT-like Deep Models to Reduce Hallucination and to Improve Reproducibility in Scientific Text Generation Using Stochastic Optimisation Techniques
by: Sulimov, Daniil
Published: (2024)

Towards Interpretable Protein Structure Prediction with Sparse Autoencoders
by: Parsan, Nithin, et al.
Published: (2025)

Beyond One-Way Pruning: Bidirectional Pruning-Regrowth for Extreme Accuracy-Sparsity Tradeoff
by: Liu, Junchen, et al.
Published: (2025)

Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit
by: Jiang, Nick, et al.
Published: (2025)