For mechanistic interpretability research, we just released a new paper on neuron interpretability in LLMs, with a large discussion on superposition! SeePaper: https://arxiv.org/abs/2305.01610Summary: https://twitter.com/wesg52/status/1653750337373880322
For mechanistic interpretability research, we just released a new paper on neuron interpretability in LLMs, with a large discussion on superposition! See
Paper: https://arxiv.org/abs/2305.01610
Summary: https://twitter.com/wesg52/status/1653750337373880322