Following Anthropic's Transformer Circuits thread.

Transformer Circuits 1: Summary of Results

2025-05-17 · 3 min read

Reading the Framework paper, part 1. Treating tiny attention-only models as model organisms for fully reverse engineering transformers, and a map of the key results.

Transformer Circuits 2: The Transformer, Redrawn

2025-05-31 · 9 min read

Reading the Framework paper, part 2. Redrawing the residual stream as a communication channel and attention heads as independent information movers, through virtual weights and the QK/OV split.

Transformer Circuits 3: Zero-Layer Transformers

2025-06-14 · 3 min read

Reading the Framework paper, part 3. What does a transformer with no attention at all learn? Bigram statistics, and that answer turns out to be the key to the direct path in large models.

Transformer Circuits 4: One-Layer Models and Skip-Trigrams

2025-06-28 · 7 min read

Reading the Framework paper, part 4. Fully expanding a one-attention-layer model into paths: skip-trigrams, copying heads and positive eigenvalues, and the characteristic bugs the factored structure produces.