© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 45828
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Harrison."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    0.6%
    11
    +0.11
    0.5%
    247
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.01
    220
    +0.11
    0.01
    11
    +0.10
    0.01
    Negative Logits
    ãĥīãĥ©
    -0.85
    sembly
    -0.78
    */(
    -0.75
    uction
    -0.74
    uyomi
    -0.73
    ãĥ³
    -0.72
    unin
    -0.71
    cham
    -0.70
    ctive
    -0.69
    gently
    -0.69
    POSITIVE LOGITS
    burg
    1.16
     Harrison
    0.89
    burgh
    0.84
     Ford
    0.82
    ano
    0.81
    aldi
    0.81
     Vaugh
    0.80
    aged
    0.80
     Barnes
    0.76
    inson
    0.76
    Activations Density 0.005%

    No Known Activations