SERI MATS

Applied to Clarifying mesa-optimization by Marius Hobbhahn 9d ago

Applied to Empirical risk minimization is fundamentally confused by Jesse Hoogland 9d ago

Applied to Natural Abstractions: Key claims, Theorems, and Critiques by Erik Jenner 15d ago

Applied to [Appendix] Natural Abstractions: Key Claims, Theorems, and Critiques by Erik Jenner 15d ago

Applied to Understanding and controlling a maze-solving policy network by Ryan Kidd 19d ago

Applied to A mechanistic explanation for SolidGoldMagikarp-like tokens in GPT2 by Stefan Heimersheim 22d ago

Applied to Why are counterfactuals elusive? by Ryan Kidd 1mo ago

Applied to Predictions for shard theory mechanistic interpretability results by Alex Turner 1mo ago

Applied to Searching for a model's concepts by their shape – a theoretical framework by Kaarel 1mo ago

Applied to Intervening in the Residual Stream by Ryan Kidd 1mo ago

Applied to A Neural Network undergoing Gradient-based Training as a Complex System by Spencer Becker-Kahn 1mo ago

Applied to The shallow reality of 'deep learning theory' by Jesse Hoogland 1mo ago

Applied to Qualities that alignment mentors value in junior researchers by Akash 2mo ago

Applied to A circuit for Python docstrings in a 4-layer attention-only transformer 2mo ago

Applied to SERI ML Alignment Theory Scholars Program 2022 by elifland 2mo ago

Applied to SolidGoldMagikarp II: technical details and more recent findings by Ryan Kidd 2mo ago

Applied to [ASoT] Policy Trajectory Visualization by David Udell 2mo ago

Applied to Gradient surfing: the hidden role of regularization by Jesse Hoogland 2mo ago