相关论文: Improving Steering Vectors by Targeting Sparse Aut…

As an important problem in causal inference, we discuss the identification and estimation of treatment effects (TEs) under limited overlap; that is, when subjects with certain features belong to a single treatment group. We use a latent…

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…

Sparse Autoencoders (SAEs) have emerged as a promising solution for decomposing large language model representations into interpretable features. However, Paulo and Belrose (2025) have highlighted instability across different initialization…

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…

Targeted syntactic evaluation of subject-verb number agreement in English (TSE) evaluates language models' syntactic knowledge using hand-crafted minimal pairs of sentences that differ only in the main verb's conjugation. The method…

Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing a practical middle ground between prompting and fine-tuning. Yet SVs can be unreliable in…

Latent steering exploits internal representations of Large Language Models (LLMs) to guide generation, yet interventions on dense states can entangle distinct semantic features. In this paper, we investigate attention query activations as a…

For large language models (LLMs), sparse autoencoders (SAEs) have been shown to decompose intermediate representations that often are not interpretable directly into sparse sums of interpretable features, facilitating better control and…

We train nine sparse autoencoders (SAEs) on the residual stream of Qwen 3.5-35B-A3B, a 35-billion-parameter Mixture-of-Experts model with a hybrid GatedDeltaNet/attention architecture, and use them to identify and steer five agentic…

In recent years, pre-trained large language models have achieved remarkable success across diverse tasks. Besides the pivotal role of self-supervised pre-training, their effectiveness in downstream applications also depends critically on…

Variational autoencoders (VAEs) have been used extensively to discover low-dimensional latent factors governing neural activity and animal behavior. However, without careful model selection, the uncovered latent factors may reflect noise in…

The mechanisms behind multilingual capabilities in Large Language Models (LLMs) have been examined using neuron-based or internal-activation-based methods. However, these methods often face challenges such as superposition and layer-wise…

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…

Sparse Autoencoders (SAEs) provide potentials for uncovering structured, human-interpretable representations in Large Language Models (LLMs), making them a crucial tool for transparent and controllable AI systems. We systematically analyze…

Recent work shows that Sparse Autoencoders (SAE) applied to large language model (LLM) layers have neurons corresponding to interpretable concepts. These SAE neurons can be modified to align generated outputs, but only towards…

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for interpreting the internal representations of large language models (LLMs), revealing latent latent features with semantical meaning. This interpretability has also…

Understanding training dynamics and feature evolution is crucial for the mechanistic interpretability of large language models (LLMs). Although sparse autoencoders (SAEs) have been used to identify features within LLMs, a clear picture of…

Linear concept vectors effectively steer LLMs, but existing methods suffer from noisy features in diverse datasets that undermine steering robustness. We propose Sparse Autoencoder-Denoised Concept Vectors (SDCV), which selectively keep the…

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…

The rapid advancements in transformer-based language models have revolutionized natural language processing, yet understanding the internal mechanisms of these models remains a significant challenge. This paper explores the application of…