tangermeme merges DeepLIFT/SHAP extension bringing attribution to arbitrary models
jmschreiber91 · x · 2026-10-18
tangermeme has merged an extension of DeepLIFT/SHAP: closed-form solutions for LayerNorm/RMSNorm work out-of-the-box, and an integrated-gradients approximation covers any non-linear operation (slower but general). This fixes prior unsupported channel/position-mixing normalizations; an updated tangermeme skill now guides agents on using it.
More from Research
- Paper argues mechanistic interpretability needs a rigorous "logic of inference" — burny_tech · 2026-10-18
- NeurIPS 2026 Journal Track accepts 88 papers from TMLR, JMLR, AoS — NeurIPSConf · 2026-10-18
- RCT: AI-generated layperson summaries of medical findings improve visit quality and shorten consultations — EricTopol · 2026-10-18
- Progress on mapping jev's j-space — sloppenheimer · 2026-10-18
- Hand-probing tiny model neurons: gate is swappable, down steers it into an owl — maxsloef · 2026-10-18
- MIT paper builds attention-based foundation model for quantum states, 18 training points suffice — jwt0625 · 2026-10-18