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. 6761
    Prev
    Next
    INDEX
    Explanations

    names related to the name "Kane"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly focusing on the character Kane

    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
    psons
    -0.84
    iments
    -0.78
    reen
    -0.77
    ended
    -0.75
    perse
    -0.75
    reek
    -0.73
    azeera
    -0.71
    awaru
    -0.70
    owship
    -0.70
    uez
    -0.69
    POSITIVE LOGITS
     Hots
    1.02
     Kane
    1.02
    hyde
    0.80
    zie
    0.77
     Bryant
    0.73
    zan
    0.72
    zeb
    0.71
     Noon
    0.71
    vill
    0.71
    holder
    0.71
    Activations Density 0.021%

    No Known Activations