In Fig. 7, we see that a lot of the nOK samples are clearly bent, however…
Tag: Inspection
Open the Synthetic Mind: Sparse Autoencoders for LLM Inspection | by Salvatore Raieli | Nov, 2024
|LLM|INTERPRETABILITY|SPARSE AUTOENCODERS|XAI| A deep dive into LLM visualization and interpretation utilizing sparse autoencoders Picture created by…