Transformers Use Causal World Models in Maze-Solving Tasks

• URL: http://arxiv.org/abs/2412.11867v1
• Date: Mon, 16 Dec 2024 15:21:04 GMT
• Title: Transformers Use Causal World Models in Maze-Solving Tasks
• Authors: Alex F. Spies, William Edwards, Michael I. Ivanitskiy, Adrians Skapars, Tilman Räuker, Katsumi Inoue, Alessandra Russo, Murray Shanahan,
• Abstract summary: We investigate the inner workings of transformer models trained on tasks across various domains. We find that transformers are able to reason with respect to a greater number of active features than they see during training. We observe that varying positional encodings can alter how WMs are encoded in a model's residual stream.
• Score: 49.67445252528868
• License:
• Abstract: Recent studies in interpretability have explored the inner workings of transformer models trained on tasks across various domains, often discovering that these networks naturally develop surprisingly structured representations. When such representations comprehensively reflect the task domain's structure, they are commonly referred to as ``World Models'' (WMs). In this work, we discover such WMs in transformers trained on maze tasks. In particular, by employing Sparse Autoencoders (SAEs) and analysing attention patterns, we examine the construction of WMs and demonstrate consistency between the circuit analysis and the SAE feature-based analysis. We intervene upon the isolated features to confirm their causal role and, in doing so, find asymmetries between certain types of interventions. Surprisingly, we find that models are able to reason with respect to a greater number of active features than they see during training, even if attempting to specify these in the input token sequence would lead the model to fail. Futhermore, we observe that varying positional encodings can alter how WMs are encoded in a model's residual stream. By analyzing the causal role of these WMs in a toy domain we hope to make progress toward an understanding of emergent structure in the representations acquired by Transformers, leading to the development of more interpretable and controllable AI systems.

Related papers

• Interpreting and Steering Protein Language Models through Sparse Autoencoders [0.9208007322096533]
  This paper explores the application of sparse autoencoders to interpret the internal representations of protein language models. By performing a statistical analysis on each latent component's relevance to distinct protein annotations, we identify potential interpretations linked to various protein characteristics. We then leverage these insights to guide sequence generation, shortlisting the relevant latent components that can steer the model towards desired targets.
  arXiv  Detail & Related papers  (2025-02-13T10:11:36Z)
• Analyzing Fine-tuning Representation Shift for Multimodal LLMs Steering alignment [53.90425382758605]
  We show how fine-tuning alters the internal structure of a model to specialize in new multimodal tasks. Our work sheds light on how multimodal representations evolve through fine-tuning and offers a new perspective for interpreting model adaptation in multimodal tasks.
  arXiv  Detail & Related papers  (2025-01-06T13:37:13Z)
• Interpreting Affine Recurrence Learning in GPT-style Transformers [54.01174470722201]
  In-context learning allows GPT-style transformers to generalize during inference without modifying their weights. This paper focuses specifically on their ability to learn and predict affine recurrences as an ICL task. We analyze the model's internal operations using both empirical and theoretical approaches.
  arXiv  Detail & Related papers  (2024-10-22T21:30:01Z)
• Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures [49.24097977047392]
  We investigate two mainstream architectures for language modeling, namely Transformers and Mambas, to explore the extent of their mechanistic similarity. We propose to use Sparse Autoencoders (SAEs) to isolate interpretable features from these models and show that most features are similar in these two models.
  arXiv  Detail & Related papers  (2024-10-09T08:28:53Z)
• Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models [22.89563355840371]
  We study the modularity of neural networks by analyzing circuits for highly compositional subtasks within a language model. Our results indicate that functionally similar circuits exhibit both notable node overlap and cross-task faithfulness.
  arXiv  Detail & Related papers  (2024-10-02T11:36:45Z)
• Computation-Efficient Era: A Comprehensive Survey of State Space Models in Medical Image Analysis [8.115549269867403]
  State Space Models (SSMs) have garnered immense interest lately in sequential modeling and visual representation learning. Capitalizing on the advances in computer vision, medical imaging has heralded a new epoch with Mamba models.
  arXiv  Detail & Related papers  (2024-06-05T16:29:03Z)
• A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task [14.921790126851008]
  We present a comprehensive mechanistic analysis of a transformer trained on a synthetic reasoning task. We identify a set of interpretable mechanisms the model uses to solve the task, and validate our findings using correlational and causal evidence.
  arXiv  Detail & Related papers  (2024-02-19T08:04:25Z)
• Understanding Addition in Transformers [2.07180164747172]
  This paper provides a comprehensive analysis of a one-layer Transformer model trained to perform n-digit integer addition. Our findings suggest that the model dissects the task into parallel streams dedicated to individual digits, employing varied algorithms tailored to different positions within the digits.
  arXiv  Detail & Related papers  (2023-10-19T19:34:42Z)
• A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks [60.38369406877899]
  Transformer is a deep neural network that employs a self-attention mechanism to comprehend the contextual relationships within sequential data. transformer models excel in handling long dependencies between input sequence elements and enable parallel processing. Our survey encompasses the identification of the top five application domains for transformer-based models.
  arXiv  Detail & Related papers  (2023-06-11T23:13:51Z)
• VisBERT: Hidden-State Visualizations for Transformers [66.86452388524886]
  We present VisBERT, a tool for visualizing the contextual token representations within BERT for the task of (multi-hop) Question Answering. VisBERT enables users to get insights about the model's internal state and to explore its inference steps or potential shortcomings.
  arXiv  Detail & Related papers  (2020-11-09T15:37:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.