© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 7929
    Prev
    Next
    INDEX
    Explanations

    references related to geographical locations or sports teams, especially focusing on "Jersey Shore" and "New Jersey Devils"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    587
    +0.10
    0.4%
    721
    +0.09
    0.4%
    288
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.10
    0.02
    587
    +0.09
    0.02
    219
    +0.09
    0.01
    Negative Logits
    66666666
    -0.74
    mble
    -0.72
    fare
    -0.70
    byss
    -0.70
    erness
    -0.66
    sheet
    -0.66
    BOOK
    -0.65
    ware
    -0.65
    esome
    -0.64
    rients
    -0.63
    POSITIVE LOGITS
     Devils
    1.22
     Shore
    1.00
     Nets
    0.90
     Devil
    0.83
     Transit
    0.81
     Jersey
    0.78
    ilee
    0.73
     Advance
    0.73
    idia
    0.72
     Yards
    0.71
    Activations Density 0.024%

    No Known Activations