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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 22479
    Prev
    Next
    INDEX
    Explanations

    mentions of names or entities, particularly 'Cody' or 'Jody.'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "body" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    keye
    -1.01
    keyes
    -0.78
    ilit
    -0.71
    ugal
    -0.69
    itude
    -0.68
    uckland
    -0.68
    ushi
    -0.65
    umar
    -0.65
    eties
    -0.65
    arak
    -0.64
    POSITIVE LOGITS
    mble
    0.97
    issance
    0.90
    EStream
    0.88
    uality
    0.88
    lus
    0.83
    etsk
    0.81
    brance
    0.79
    soDeliveryDate
    0.77
    tz
    0.76
    obyl
    0.74
    Activations Density 0.045%

    No Known Activations