Automates attribution-graph analysis via probe prompting: circuit-trace a prompt, auto-generate concept probes, profile feature activations, cluster supernodes.

Reproducible case study of pitfalls in contrastive SAE discovery and steering for "consciousness" features (GemmaScope SAEs, Gemma 3 4B/12B): reconstruction confound, delta-steering fix, matched controls, and false-positive scaling law vs dataset size.

Explore limitations of contrastive SAE steering in identifying causal consciousness features and introduce delta-steering to improve experiment validity.

Finding SAE features in Gemma 3 vision-language model — autonomous AI vs human-guided AI comparison using GemmaScope 2

Use GemmaScope and Neuronpedia features to steer Gemma 3 4B IT locally