Neuronpedia Supports Research Analysis
simi_97k · x · 2026-07-12
The author mentioned that the paper's appendix includes dashboards for the aforementioned features, which are hosted on Neuronpedia.
They expressed gratitude for this open interpretability tool, which made the analysis of cultural bias and steering much more convenient to conduct.
Related event: Limitations and Tooling for Cultural Steering Methods(2 posts)→
More from Research
- Fixing compute convention and fitted floor cuts scaling forecast error ~79% — dlwh · 2026-10-27
- Retrospective: Hero scaling forecast fixed without using Hero losses, code open-sourced — dlwh · 2026-10-27
- Scaling-fit discrepancy: output-head FLOPs are ~65% of compute at the smallest rung, ~3% at 535B — dlwh · 2026-10-27
- Marin's dlwh Explains the Scaling Law Fit: Estimating the Loss Floor Early — dlwh · 2026-10-27
- Marin's Open Scaling Law Extrapolates 300× and Predicts Loss Within 0.2% — dlwh · 2026-10-27
- Delegating scaling-law asymptote fitting to Codex while planning a birthday party — dlwh · 2026-10-27