paper-with-me

Papers

Adaptive Circuit Behavior and Generalization in Mechanistic Interpretability

2024-11-25 · Jatin Nainani, Sankaran Vaidyanathan, AJ Yeung, Kartik Gupta, David Jensen

Mechanistic interpretability aims to understand the inner workings of large neural networks by identifying circuits, or minimal subgraphs within the model that implement algorithms responsible for performing specific tasks. These circuits are typically discovered and analyzed using a narrowly defined prompt format. However, given the abilities of large language models (LLMs) to generalize across various prompt formats for the same task, it remains unclear how well these circuits generalize. For instance, it is unclear whether the models generalization results from reusing the same circuit components, the components behaving differently, or the use of entirely different components. In this paper, we investigate the generality of the indirect object identification (IOI) circuit in GPT-2 small, which is well-studied and believed to implement a simple, interpretable algorithm. We evaluate its performance on prompt variants that challenge the assumptions of this algorithm. Our findings reveal that the circuit generalizes surprisingly well, reusing all of its components and mechanisms while only adding additional input edges. Notably, the circuit generalizes even to prompt variants where the original algorithm should fail; we discover a mechanism that explains this which we term S2 Hacking. Our findings indicate that circuits within LLMs may be more flexible and general than previously recognized, underscoring the importance of studying circuit generalization to better understand the broader capabilities of these models.

📄 PDF Abstract BibTeX arXiv:2411.16105

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

An explainable transformer circuit for compositional generalization

2025-02-19 · Cheng Tang, Brenden Lake, Mehrdad Jazayeri

Compositional generalization-the systematic combination of known components into novel structures-remains a core challenge in cognitive science and machine learning. Although transformer-based large language models can e…

Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future Directions

2026-01-21 · Usman Naseem arxiv

Large language models (LLMs) have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque. Mechanistic interpretability (i.e., the systematic study of how…

Reinforcement Learning

Towards Automated Circuit Discovery for Mechanistic Interpretability

2023-04-28 · NeurIPS 2023 11 · Arthur Conmy, Augustine N. Mavor-Parker, Aengus Lynch, Stefan Heimersheim 외

Through considerable effort and intuition, several recent works have reverse-engineered nontrivial behaviors of transformer models. This paper systematizes the mechanistic interpretability process they followed. First, r…

Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers

2026-04-15 · Nina Żukowska, Wolfgang Stammer, Bernt Schiele, Jonas Fischer arxiv

Transparency of neural networks' internal reasoning is at the heart of interpretability research, adding to trust, safety, and understanding of these models. The field of mechanistic interpretability has recently focused…

Scalable Circuit Learning for Interpreting Large Language Models

2026-06-15 · Naiyu Yin, Dennis Wei, Tian Gao, Amit Dhurandhar 외 arxiv

A prominent research direction in mechanistic interpretability is learning sparse circuits over LLM components to reveal how they jointly produce model behavior. However, raw neurons are polysemantic, making learned circ…