Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 8860
    Prev
    Next
    INDEX
    Explanations

    organizations and entities related to health, associations, societies, and institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to various organizations, societies, and authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pollen
    -0.74
    storms
    -0.71
     warming
    -0.70
    artist
    -0.68
     unfavorable
    -0.66
     brewer
    -0.65
    itures
    -0.64
     clim
    -0.63
    lasses
    -0.61
     bir
    -0.61
    POSITIVE LOGITS
     Suite
    0.96
     Syndicate
    0.91
     Of
    0.91
     of
    0.90
     Franch
    0.89
     Interface
    0.89
     Accountability
    0.85
     Ltd
    0.84
     Maurit
    0.82
     Digest
    0.79
    Activations Density 0.273%

    No Known Activations