RSS

Lucy Farnik

Karma: 84

PhDing in AI safety, currently poking at computational sparsity in LLMs

[PAPER] Ja­co­bian Sparse Au­toen­coders: Spar­sify Com­pu­ta­tions, Not Just Activations

Lucy Farnik26 Feb 2025 12:50 UTC
79 points
8 comments7 min readLW link