Researcher likens steering vectors vs mech interp to heritability vs GWAS convergence
moultano · x · 2026-10-17
Google researcher moultano offers a methodological analogy: the relationship between steering vectors and mechanistic interpretability may come to resemble that between heritability estimates and GWAS—two approaches improved iteratively in the hope they eventually meet in the middle.
More from Research
- HF Transformers adds activation checkpoint offloading to CPU to free GPU memory — StasBekman · 2026-10-17
- S4VY: Segment Anything in 4D, with consistent identity across space and time — realChrisChoy · 2026-10-17
- TF-MoDISco optimization merged: 5-15x speedup, 2-3x memory savings, identical output — anshulkundaje · 2026-10-17
- Apple releases RSI-Inference Bench: best agent solves just 26.7% of vLLM/SGLang tasks — SumitGup · 2026-10-17
- Satoshi's distrust of NIST seeds revisited: Claude's P256 discovery shows it wasn't needed — StefanoGogioso · 2026-10-17
- TMS Paper Is Under-Appreciated: Polysemanticity Lives in Weak Activations — livgorton · 2026-10-17