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. 5-RES-JB
    6. 14275
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to sports teams

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to specific teams, locations, and individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugal
    -0.77
    initely
    -0.75
    isting
    -0.73
    axter
    -0.72
    ista
    -0.68
     Emerson
    -0.68
     hunger
    -0.68
    istor
    -0.67
    ando
    -0.66
    ists
    -0.66
    POSITIVE LOGITS
    enegger
    0.90
    creen
    0.79
    DAY
    0.73
    lus
    0.71
     Boll
    0.71
    kus
    0.67
    orage
    0.67
    mber
    0.66
     Squirrel
    0.66
    vine
    0.66
    Activations Density 0.048%

    No Known Activations