A Training-Time Sign Flip in IOI Circuit Formation : Code, data and analyses for paper accepted at the ICML 2026 Mechanistic Interpretability Workshop.
Watching features form during Pythia training
Developmental Atlas of Attention Head Specialization: Spacing, Stranding, and the Capacity Tax of BPE Tokenization. ~50% of attention heads in standard BPE are mandatory whitespace boundary recovery. Merge barriers eliminate the tax.
Does an SLT Local Learning Coefficient change in step with a small LM acquiring Portuguese grammar?
Longitudinal study of syntactic emergence in Pythia (BLiMP/Zorro) and its alignment with human language acquisition — U-shaped learning curves & age-of-acquisition correlation. NLP research project, ACL-format paper.
Monitor AI usage caps for GPT, Claude, and Grok in one clean, local-first dashboard.
To associate your repository with the developmental-interpretability topic, visit your repo's landing page and select "manage topics."