Sparse Autoencoders of Diffusion Language Models (Dream-7B, LLaDA-8B) and Large Language Models (Qwen-2.5-7B, LLaMA-3-8B)
XWang
AwesomeInterpretability
AI & ML interests
None yet
Organizations
None yet
models 13
AwesomeInterpretability/dream-mask-jumprelu_gated-sae
Updated
AwesomeInterpretability/llada-mask-topk-32K_65K-sae
Updated
AwesomeInterpretability/dream-mask-topk-32K_65K-sae
Updated
AwesomeInterpretability/llada-unmask-topk-sae
Feature Extraction • Updated
AwesomeInterpretability/llada-mask-topk-sae
Feature Extraction • Updated
AwesomeInterpretability/dream-sft-mask-topk-sae
Updated
AwesomeInterpretability/qwen-topk-sae
Updated
AwesomeInterpretability/llama-topk-sae
Updated
AwesomeInterpretability/dlm-mask-topk-sae
Updated • 2
AwesomeInterpretability/dlm-unmask-topk-sae
Updated
datasets 0
None public yet