Related papers: Don't Forget It! Conditional Sparse Autoencoder Cl…

Vision-language models (VLMs) have advanced rapidly and are increasingly deployed in real-world applications, especially with the rise of agent-based systems. However, their safety has received relatively limited attention. Even the latest…

A recent line of work has shown promise in using sparse autoencoders (SAEs) to uncover interpretable features in neural network representations. However, the simple linear-nonlinear encoding mechanism in SAEs limits their ability to perform…

Sparse autoencoders (SAEs) have recently become central tools for interpretability, leveraging dictionary learning principles to extract sparse, interpretable features from neural representations whose underlying structure is typically…

Recently, large language models (LLMs) have emerged as a notable field, attracting significant attention for its ability to automatically generate intelligent contents for various application domains. However, LLMs still suffer from…

Sparse autoencoders (SAEs) are a popular method for decomposing Large Langage Models (LLM) activations into interpretable latents. However, due to their substantial training cost, most academic research uses open-source SAEs which are only…

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…

Developing human understandable interpretation of large language models (LLMs) becomes increasingly critical for their deployment in essential domains. Mechanistic interpretability seeks to mitigate the issues through extracts…

Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scalability, and a lack…

Sparse autoencoders (SAEs) are widely used for interpreting language model activations. A key evaluation metric is the increase in cross-entropy loss between the original model logits and the reconstructed model logits when replacing model…

Sparse autoencoders (SAEs) are used to decompose neural network activations into human-interpretable features. Typically, features learned by a single SAE are used for downstream applications. However, it has recently been shown that SAEs…

As Large Language Models become integral to software development, with substantial portions of AI-suggested code entering production, understanding their internal correctness mechanisms becomes critical for safe deployment. We apply sparse…

Sparse Autoencoders (SAEs) are widely employed for mechanistic interpretability and model steering. Within this context, steering is by design performed by means of decoding altered SAE intermediate representations. This procedure…

Large language models (LLMs) have achieved remarkable progress, yet their internal mechanisms remain largely opaque, posing a significant challenge to their safe and reliable deployment. Sparse autoencoders (SAEs) have emerged as a…

Sparse autoencoders (SAEs) are a promising unsupervised approach for identifying causally relevant and interpretable linear features in a language model's (LM) activations. To be useful for downstream tasks, SAEs need to decompose LM…

Protein language models (PLMs) have demonstrated remarkable success in protein modeling and design, yet their internal mechanisms for predicting structure and function remain poorly understood. Here we present a systematic approach to…

It is assumed that sparse autoencoders (SAEs) decompose polysemantic activations into interpretable linear directions, as long as the activations are composed of sparse linear combinations of underlying features. However, we find that if an…

Large Language Models (LLMs) are trained on massive, unstructured corpora, making it unclear which social patterns and biases they absorb and later reproduce. Existing evaluations typically examine outputs or activations, but rarely connect…

Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their…

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…

Sparse autoencoders (SAEs) have emerged as a powerful technique for extracting human-interpretable features from neural networks activations. Previous works compared different models based on SAE-derived features but those comparisons have…