arxiv:2602.14111
Anton Korznikov
AntonKorznikov
AI & ML interests
None yet
Recent Activity
authored a paper about 7 hours ago
The Rogue Scalpel: Activation Steering Compromises LLM Safety upvoted a paper about 10 hours ago
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs updated a model 2 months ago
AntonKorznikov/random_saeOrganizations
None yet
models 13
AntonKorznikov/random_sae
Updated • 1
AntonKorznikov/SparseTransformer
Updated
AntonKorznikov/trained_saes
Updated
AntonKorznikov/llama_rebuttal_matr2
Updated
AntonKorznikov/llama_rebuttal_matr
Updated
AntonKorznikov/llama_rebuttal
Updated
AntonKorznikov/gemma_rebuttal
Updated
AntonKorznikov/skip
Updated
AntonKorznikov/additional_exps
Updated
AntonKorznikov/testing_saes_1
Updated