Related papers: Scaling sparse feature circuit finding for in-cont…

In-context learning (ICL) exhibits dual operating modes: task learning, i.e., acquiring a new skill from in-context samples, and task retrieval, i.e., locating and activating a relevant pretrained skill. Recent theoretical work investigates…

Sparse autoencoders (SAEs) are a promising approach for uncovering interpretable features in large language models (LLMs). While several automated evaluation methods exist for SAEs, most rely on external LLMs. In this work, we introduce…

Sparse autoencoders (SAEs) trained on large language model activations output thousands of features that enable mapping to human-interpretable concepts. The current practice for analyzing these features primarily relies on inspecting…

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging, especially in open-ended generation settings. This paper…

Sparse autoencoders (SAEs) have proven effective for extracting monosemantic features from large language models (LLMs), yet these features are typically identified in isolation. However, broad evidence suggests that LLMs capture the…

Sparse Autoencoders (SAEs) are powerful tools for interpreting neural representations, yet their use in audio remains underexplored. We train SAEs across all encoder layers of Whisper and HuBERT, provide an extensive evaluation of their…

Is there really much more to say about sparse autoencoders (SAEs)? Autoencoders in general, and SAEs in particular, represent deep architectures that are capable of modeling low-dimensional latent structure in data. Such structure could…

In-context Learning (ICL) is an emerging few-shot learning paradigm based on modern Language Models (LMs), yet its inner mechanism remains unclear. In this paper, we investigate the mechanism through a novel perspective of information…

Large language models (LLMs) demonstrate exceptional performance on tasks requiring complex linguistic abilities, such as reference disambiguation and metaphor recognition/generation. Although LLMs possess impressive capabilities, their…

Sparse Autoencoders (SAEs) are increasingly used to interpret foundation models, but their role as an actionable intervention space remains less understood, especially in vision. We study whether sparse visual features can be used not only…

Sparse Autoencoders (SAEs) decompose large language model representations into interpretable features, but how these features interact under uncertainty remains poorly understood. We introduce Feature Rivalry -- negatively correlated SAE…

Circuit analysis of any certain model behavior is a central task in mechanistic interpretability. We introduce our circuit discovery pipeline with Sparse Autoencoders (SAEs) and a variant called Transcoders. With these two modules inserted…

In-context learning (ICL) has emerged as a powerful paradigm for easily adapting Large Language Models (LLMs) to various tasks. However, our understanding of how ICL works remains limited. We explore a simple model of ICL in a controlled…

Large language models have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque, limiting our ability to inspect, control, and systematically improve them. This opacity…

Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through additional training, we explore an alternative: steering model…

Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large…

Sparse Autoencoders (SAEs) are widely used to steer large language models (LLMs), based on the assumption that their interpretable features naturally enable effective model behavior steering. Yet, a fundamental question remains unanswered:…

Sparse autoencoders (SAEs) are used to decompose neural network activations into sparsely activating features, but many SAE features are only interpretable at high activation strengths. To address this issue we propose to use binary sparse…

Sparse autoencoders provide a promising unsupervised approach for extracting interpretable features from a language model by reconstructing activations from a sparse bottleneck layer. Since language models learn many concepts, autoencoders…

Audio pretrained models are widely employed to solve various tasks in speech processing, sound event detection, or music information retrieval. However, the representations learned by these models are unclear, and their analysis mainly…