community
active
leiden_hybrid_concepts
label: haiku
community:leiden_hybrid_concepts-run4-c0-c1-c5Convergent interpretability across neural architectures
Studies showing that learned feature representations and interpretable directions emerge consistently across different model designs and scales.
2 members. Each node is clickable.
Loading graph…
Drawn from 2 sources
The papers/notes whose extracted claims & findings make up this cluster.
- Explaining 4.2 million genetic variants with state-of-the-art, interpretable predictions1 member
- RESEARCH-VECTORS.md1 member
Bridges (3)
Other communities that share members with this one — cross-cutting threads or papers that sit at the seam between two themes.
Claims (2)
- Interpretable predictions can help resolve variants of uncertain significanceMotivating claim that mechanistic explanations add clinical value for VUS.
- Interpretability features converge across different model architectures, revealing structural similarities.