Subscribe
Topic

Transformer Architecture

How transformers learn and how researchers study them. Posts explain in-context learning through induction heads and attention circuits, activation patching and causal tracing, and the causes of loss spikes in LLM training.

Articles

1-3
  1. Activation Patching and Causal Tracing: Mathematical Foundations, Counterfactual Interventions, and Circuit Discovery in Large Language Models

    Activation Patching and Causal Tracing: Mathematical Foundations, Counterfactual Interventions, and Circuit Discovery in Large Language Models Mechanistic interpretability aims to reverse-engineer the computational graphs implemented by trained neural networks into human-understandable algorithms. In autoregressive Transformer models, standard observational tools such as attention map visualization and linear probing often fail to distinguish between active computational paths and passive corre

    Education
    8 min read
  2. Loss Spikes and Training Stability in Large Language Models: How Attention Logit Drift, z-loss, and QK-Norm Prevent Gradient Explosions

    During the pre-training of modern large language models, few operational failures are as costly as loss spikes. When training clusters containing thousands of GPUs run for weeks across trillions of tokens, a sudden, discontinuous surge in cross-entropy loss can corrupt optimizer momentum buffers, induce numerical overflow in half-precision representations, and permanently degrade downstream model capabilities. In severe cases, models experience catastrophic divergence, forcing engineering teams

    AI
    11 min read
  3. In-Context Learning in Large Language Models: How Induction Heads and Attention Circuits Learn Without Weight Updates

    Autoregressive large language models demonstrate the ability to adapt to new tasks, follow few-shot demonstrations, and execute algorithmic patterns entirely within their context windows. Unlike traditional fine-tuning, in-context learning occurs at inference time with frozen model parameters, leaving weights completely unchanged ($\Delta \theta = 0$). For several years following the scaling demonstrations in GPT-3, the internal mechanism governing in-context learning remained an empirical blac

    AI
    6 min read