Jacobian Lens (J-Lens) and J-Space Toolkit for transformer mechanistic interpretability. Train linear lenses, decompose hidden states, and run causal interventions on decoder-only models.
Mechanistic interpretability of multilingual reasoning in transformers. 170+ causal intervention experiments across 4 model families.
An independent, from-scratch reproduction of the mechanistic-interpretability findings in Anthropic's When Models Manipulate Manifolds: The Geometry of a Counting Task
Evaluate mechanistic estimates through the interventions, control loops, and safety decisions they guide.
Mechanistic study of contextual-integrity post-training in Qwen2.5-7B, testing whether improved privacy behavior comes from new mechanisms or better use of machinery already present in the base model.
Code for SCIT: cache-level causal diagnostics for latent chain-of-thought models (EMNLP 2026 Findings)
Mechanistic interpretability of code models through probing, perturbations, and causal interventions
A controlled mechanistic interpretability study testing whether representation–self-report alignment survives a targeted modification to a language model.
Behavioral auditing of finetuned language models using blinded policy recovery, model diffing, and causal activation interventions.
To associate your repository with the causal-interventions topic, visit your repo's landing page and select "manage topics."