Related papers: Sparse Autoencoders Find Highly Interpretable Feat…
A key barrier to interpreting large language models is polysemanticity, where neurons activate for multiple unrelated concepts. Sparse autoencoders (SAEs) have been proposed to mitigate this issue by transforming dense activations into…
While the activations of neurons in deep neural networks usually do not have a simple human-understandable interpretation, sparse autoencoders (SAEs) can be used to transform these activations into a higher-dimensional latent space which…
Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures, recent evidence suggests that neural networks encode…
Recent work in Mechanistic Interpretability (MI) has enabled the identification and intervention of internal features in Large Language Models (LLMs). However, a persistent challenge lies in linking such internal features to the reliable…
Recent advances in explainable machine learning have highlighted the potential of sparse autoencoders in uncovering mono-semantic features in densely encoded embeddings. While most research has focused on Large Language Model (LLM)…
Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for decomposing the internal activations of trained transformers into sparse,…
To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…
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…
Understanding the multilingual mechanisms of large language models (LLMs) provides insight into how they process different languages, yet this remains challenging. Existing studies often focus on individual neurons, but their polysemantic…
Working in high-dimensional latent spaces, the internal encoding of data in Variational Autoencoders becomes naturally sparse. We discuss this known but controversial phenomenon sometimes refereed to as overpruning, to emphasize the…
Recent LLMs like DeepSeek-R1 have demonstrated state-of-the-art performance by integrating deep thinking and complex reasoning during generation. However, the internal mechanisms behind these reasoning processes remain unexplored. We…
We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give a stylized analysis showing that sparsity-regularized decoding can preferentially retain…
Sparse autoencoders (SAEs) have gained a lot of attention as a promising tool to improve the interpretability of large language models (LLMs) by mapping the complex superposition of polysemantic neurons into monosemantic features and…
Single neurons in neural networks are often interpretable in that they represent individual, intuitively meaningful features. However, many neurons exhibit $\textit{mixed selectivity}$, i.e., they represent multiple unrelated features. A…
Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning methods such as Sparse Autoencoders (SAEs) provide a promising…
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 uncover thousands of features in vision models, yet explaining these features without requiring human intervention remains an open challenge. While previous work has proposed generating correlation-based explanations…
Despite substantial efforts, neural network interpretability remains an elusive goal, with previous research failing to provide succinct explanations of most single neurons' impact on the network output. This limitation is due to the…
This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, namely computational…
Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demonstrated promise in this domain by extracting interpretable…