Image de couverture de livre

BatchTopK Sparse Autoencoders

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bussmann, Bart, Leask, Patrick, Nanda, Neel
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Sparse Autoencoders Do Not Find Canonical Units of Analysis
par: Leask, Patrick, et autres
Publié: (2025)

Learning Multi-Level Features with Matryoshka Sparse Autoencoders
par: Bussmann, Bart, et autres
Publié: (2025)

Are Sparse Autoencoders Useful? A Case Study in Sparse Probing
par: Kantamneni, Subhash, et autres
Publié: (2025)

Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit
par: Jiang, Nick, et autres
Publié: (2025)

Minimal and Mechanistic Conditions for Behavioral Self-Awareness in LLMs
par: Bozoukov, Matthew, et autres
Publié: (2025)

Improving Dictionary Learning with Gated Sparse Autoencoders
par: Rajamanoharan, Senthooran, et autres
Publié: (2024)

AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features
par: Zhu, Xudong, et autres
Publié: (2025)

ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions
par: Poduval, Prathyush, et autres
Publié: (2026)

Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models
par: Leask, Patrick, et autres
Publié: (2025)

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
par: Lieberum, Tom, et autres
Publié: (2024)

Explorations of Self-Repair in Language Models
par: Rushing, Cody, et autres
Publié: (2024)

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
par: Zhang, Fred, et autres
Publié: (2023)

Bidirectional Variational Autoencoders
par: Kosko, Bart, et autres
Publié: (2025)

Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control
par: Makelov, Aleksandar, et autres
Publié: (2024)

Convergent Linear Representations of Emergent Misalignment
par: Soligo, Anna, et autres
Publié: (2025)

Sparse Autoencoders, Again?
par: Lu, Yin, et autres
Publié: (2025)

Are Sparse Autoencoder Benchmarks Reliable?
par: Chanin, David
Publié: (2026)

Model Organisms for Emergent Misalignment
par: Turner, Edward, et autres
Publié: (2025)

Understanding Reasoning in Thinking Language Models via Steering Vectors
par: Venhoff, Constantin, et autres
Publié: (2025)

Base Models Know How to Reason, Thinking Models Learn When
par: Venhoff, Constantin, et autres
Publié: (2025)

Improving Sparse Autoencoder with Dynamic Attention
par: Wang, Dongsheng, et autres
Publié: (2026)

Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers
par: Ji, Xiaotong, et autres
Publié: (2026)

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
par: Ferrando, Javier, et autres
Publié: (2024)

Adaptive Sparse Allocation with Mutual Choice & Feature Choice Sparse Autoencoders
par: Ayonrinde, Kola
Publié: (2024)

Empirical Evaluation of Progressive Coding for Sparse Autoencoders
par: Peter, Hans, et autres
Publié: (2025)

Do Sparse Autoencoders Capture Concept Manifolds?
par: Bhalla, Usha, et autres
Publié: (2026)

On the transferability of Sparse Autoencoders for interpreting compressed models
par: Gupte, Suchit, et autres
Publié: (2025)

Data Whitening Improves Sparse Autoencoder Learning
par: Saraswatula, Ashwin, et autres
Publié: (2025)

Improving Robustness In Sparse Autoencoders via Masked Regularization
par: Narayanaswamy, Vivek, et autres
Publié: (2026)

Evaluating and Designing Sparse Autoencoders by Approximating Quasi-Orthogonality
par: Lee, Sewoong, et autres
Publié: (2025)

Graph-Regularized Sparse Autoencoders for LLM Safety Steering
par: Yeon, Jehyeok, et autres
Publié: (2025)

Thought Branches: Interpreting LLM Reasoning Requires Resampling
par: Macar, Uzay, et autres
Publié: (2025)

Thought Anchors: Which LLM Reasoning Steps Matter?
par: Bogdan, Paul C., et autres
Publié: (2025)

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks
par: Karvonen, Adam, et autres
Publié: (2024)

Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder
par: Xu, Zhen, et autres
Publié: (2025)

Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry
par: Hindupur, Sai Sumedh R., et autres
Publié: (2025)

Don't Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearning
par: Khoriaty, Matthew, et autres
Publié: (2025)

Interpreting Attention Layer Outputs with Sparse Autoencoders
par: Kissane, Connor, et autres
Publié: (2024)

What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering
par: Maar, Jim, et autres
Publié: (2026)

Scaling sparse feature circuit finding for in-context learning
par: Kharlapenko, Dmitrii, et autres
Publié: (2025)