Researcher proposes using attribution graphs to predict circuit activation across prompts
burny_tech · x · 2026-10-27
burnytech sketches an interpretability research idea: using Anthropic's attribution graphs to map commonly used circuits formed via generalization, then compute/predict the probability of those circuits activating across prompt families—and hence predict output behaviors. He notes the approach extends to other interp techniques, neurons, and exact cross-input algorithms like the trigonometric circuit in the grokking modular addition toy model.
More from Research
- UC Berkeley paper: RL reweights LLM reasoning strategies rather than expanding them — burny_tech · 2026-10-27
- Dehaene lab finds a cortical map integrating integers and fractions via 7T fMRI — burny_tech · 2026-10-27
- LLM rewrites a physics paper into a clearer 12-page explainer — correctness unverified — thomasahle · 2026-10-27
- OpenAI's new math results accused of scooping community mathematician's Yang-Mills work — burny_tech · 2026-10-27
- NYC Reliable AI Meetup on Synthetic Data Set for Nov 16 with NYU's Gautam Kamath — karen_ullrich · 2026-10-27
- Meta's InteractiveWorld Benchmark Shows MLLMs Still Far from Reliable Physical Assistants — meta · 2026-10-27