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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1429
    Prev
    Next
    INDEX
    Explanations

    locations or entities related specifically to Virginia

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.14
    0.7%
    727
    +0.10
    0.5%
    99
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.13
    659
    +0.10
    0.07
    99
    +0.10
    0.06
    Negative Logits
    itude
    -0.95
    ological
    -0.79
    ovie
    -0.78
    bender
    -0.77
    iatric
    -0.76
    lime
    -0.73
    ealous
    -0.73
    nesota
    -0.72
    hift
    -0.71
    hai
    -0.70
    POSITIVE LOGITS
     Tech
    0.86
     Beach
    0.79
     Virginia
    0.71
     Scotia
    0.69
    00000
    0.67
    rology
    0.65
     Compass
    0.63
     Va
    0.62
     Staples
    0.62
     Yard
    0.62
    Activations Density 1.282%

    No Known Activations