Related papers: Control Reinforcement Learning: Interpretable Toke…

Sparse autoencoders (SAEs) are a popular method for interpreting concepts represented in large language model (LLM) activations. However, there is a lack of evidence regarding the validity of their interpretations due to the lack of a…

Sparse autoencoders (SAEs) and transcoders have become important tools for machine learning interpretability. However, measuring how interpretable they are remains challenging, with weak consensus about which benchmarks to use. Most…

Intermediate layers of large language models (LLMs) best predict human brain responses to language, one of the most robust findings in computational neurolinguistics, yet why remains mechanistically unexplained. We address this gap by…

Sparse Autoencoder (SAE) features have become essential tools for mechanistic interpretability research. SAE features are typically characterized by examining their activating examples, which are often "monosemantic" and align with human…

Recent interpretability work on large language models (LLMs) has been increasingly dominated by a feature-discovery approach with the help of proxy modules. Then, the quality of features learned by, e.g., sparse auto-encoders (SAEs), is…

Safety alignment -- training large language models (LLMs) to refuse harmful requests while remaining helpful -- is critical for responsible deployment. Prior work established that safety behaviors are governed by low-rank structures,…

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…

Deep neural networks achieve impressive performance but remain difficult to interpret and control. We present SALVE (Sparse Autoencoder-Latent Vector Editing), a unified "discover, validate, and control" framework that bridges mechanistic…

Large Language Models (LLMs) are traditionally viewed as black-box algorithms, therefore reducing trustworthiness and obscuring potential approaches to increasing performance on downstream tasks. In this work, we apply an effective LLM…

Sparse autoencoders (SAEs) have emerged as a promising approach in language model interpretability, offering unsupervised extraction of sparse features. For interpretability methods to succeed, they must identify abstract features across…

Reward models (RMs) are a core component in the post-training of large language models (LLMs), serving as proxies for human preference evaluation and guiding model alignment. However, training reliable RMs under limited resources remains…

Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). However, conventional approaches to analyzing SAEs typically rely solely on…

Goal-conditioned reinforcement learning is a crucial yet challenging algorithm which enables agents to achieve multiple user-specified goals when learning a set of skills in a dynamic environment. However, it typically requires millions of…

To meet the requirements of real-world applications, it is essential to control generations of large language models (LLMs). Prior research has tried to introduce reinforcement learning (RL) into controllable text generation while most…

Despite their strong performance, Dense Passage Retrieval (DPR) models suffer from a lack of interpretability. In this work, we propose a novel interpretability framework that leverages Sparse Autoencoders (SAEs) to decompose previously…

Sparse autoencoders (SAEs) model the activations of a neural network as linear combinations of sparsely occurring directions of variation (latents). The ability of SAEs to reconstruct activations follows scaling laws w.r.t. the number of…

Sparse autoencoders (SAEs) have recently emerged as pivotal tools for introspection into large language models. SAEs can uncover high-quality, interpretable features at different levels of granularity and enable targeted steering of the…

Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration to identify a canonical set of features is challenged by…

Large-scale pre-trained vision-language models like CLIP demonstrate remarkable zero-shot performance across diverse tasks. However, fine-tuning these models to improve downstream performance often degrades robustness against distribution…

Large Language Models (LLMs) have demonstrated remarkable capabilities in generating human-like text, but their output may not be aligned with the user or even produce harmful content. This paper presents a novel approach to detect and…