相关论文: Does Circuit Analysis Interpretability Scale? Evid…

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level…

Automated interpretability systems aim to reduce the need for human labor and scale analysis to increasingly large models and diverse tasks. Recent efforts toward this goal leverage large language models (LLMs) at increasing levels of…

Mechanistic interpretability assumes that circuit analysis becomes harder as models scale. We challenge this assumption by showing that the attention architecture matters more than parameter count. Studying three circuit types across Pythia…

A widely used strategy to discover and understand language model mechanisms is circuit analysis. A circuit is a minimal subgraph of a model's computation graph that executes a specific task. We identify a gap in existing circuit discovery…

The circuits framework in mechanistic interpretability aims to identify causally important sparse subgraphs of model components, typically evaluated by measuring necessity and sufficiency. We measure circuit reuse, the proportion of…

Achieving human-level performance on some of the Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs). However, the internal mechanism of these artifacts remains…

The debate around the interpretability of attention mechanisms is centered on whether attention scores can be used as a proxy for the relative amounts of signal carried by sub-components of data. We propose to study the interpretability of…

Attention mechanisms have improved the performance of NLP tasks while allowing models to remain explainable. Self-attention is currently widely used, however interpretability is difficult due to the numerous attention distributions. Recent…

Due to the size and complexity of modern large language models (LLMs), it has proven challenging to uncover the underlying mechanisms that models use to solve reasoning problems. For instance, is their reasoning for a specific problem…

One of the main challenges in mechanistic interpretability is circuit discovery, determining which parts of a model perform a given task. We build on the Mechanistic Interpretability Benchmark (MIB) and propose three key improvements to…

Hoffman et al (2022)'s Chinchilla paper introduced the principle of compute-optimal scaling, laying a foundation for future scaling of language models. In the years since, however, valid concerns about Chinchilla have been raised: wide…

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…

Multilingual language models achieve strong aggregate performance yet often behave unpredictably across languages, scripts, and cultures. We argue that mechanistic explanations for such models should satisfy a \emph{causal} standard: claims…

Mechanistic interpretability research seeks to reveal the inner workings of large language models, yet most work focuses on classification or generative tasks rather than summarization. This paper presents an interpretability framework for…

The role of Large Language Models (LLMs) has not been extensively explored in analog circuit design, which could benefit from a reasoning-based approach that transcends traditional optimization techniques. In particular, despite their…

CLIP is one of the most popular foundational models and is heavily used for many vision-language tasks. However, little is known about the inner workings of CLIP. To bridge this gap we propose a study to quantify the interpretability in…

Many proposed applications of neural networks in machine learning, cognitive/brain science, and society hinge on the feasibility of inner interpretability via circuit discovery. This calls for empirical and theoretical explorations of…

We present causal head gating (CHG), a scalable method for interpreting the functional roles of attention heads in transformer models. CHG learns soft gates over heads and assigns them a causal taxonomy - facilitating, interfering, or…

Large Language Models (LLMs) have shown impressive performance across a wide range of tasks. However, the size of LLMs is steadily increasing, hindering their application on computationally constrained environments. On the other hand,…

This paper tests whether large language models (LLMs) can support interpretative citation context analysis (CCA) by scaling in thick, text-grounded readings of a single hard case rather than scaling up typological labels. It foregrounds…