Understanding the inner workings of machine learning models like Transformers
is vital for their safe and ethical use. This paper presents an in-depth
analysis of a one-layer Transformer model trained for integer addition. We
reveal that the model divides the task into parallel, digit-specific streams
and employs distinct algorithms for different digit positions. Our study also
finds that the model starts calculations late but executes them rapidly. A rare
use case with high loss is identified and explained. Overall, the model's
algorithm is explained in detail. These findings are validated through rigorous
testing and mathematical modeling, contributing to the broader works in
Mechanistic Interpretability, AI safety, and alignment. Our approach opens the
door for analyzing more complex tasks and multi-layer Transformer models.

这篇论文通过深入分析一个层次的 Transformer 模型在整数加法训练中的使用，揭示了该模型将任务划分为并行的、特定于数字的流，并对不同的数字位置采用不同的算法。研究还发现模型开始计算较晚但执行较快，识别并解释了一个稀有但损失较高的使用案例。总体上，该模型的算法得到了详细解释，这些发现通过严格的测试和数学建模得到了验证，对于机制解释性、人工智能安全性和对齐等广泛领域的工作具有重要贡献。我们的方法为分析更复杂的任务和多层 Transformer 模型打开了大门。