© 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 24576
    9. 8-RES_FS24576-JB
    11. 18585
    Prev
    Next
    INDEX
    Explanations

    names of people or entities

    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
    8
    +0.12
    0.5%
    285
    +0.11
    0.5%
    235
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.02
    299
    +0.11
    0.01
    285
    +0.10
    0.01
    Negative Logits
     Debor
    -0.84
    mble
    -0.78
    nell
    -0.72
    liest
    -0.72
    lift
    -0.71
    lain
    -0.69
    ãĥ¼ãĤ¯
    -0.68
    leigh
    -0.67
    eers
    -0.66
    nels
    -0.66
    POSITIVE LOGITS
    utenant
    1.27
    ptin
    1.08
    pton
    0.94
    pper
    0.90
    plom
    0.89
    udic
    0.88
    zzle
    0.87
    ibrary
    0.87
     Lilly
    0.87
    ason
    0.84
    Activations Density 0.024%

    No Known Activations