© 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. 12031
    Prev
    Next
    INDEX
    Explanations

    web development related words

    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
    113
    +0.10
    0.5%
    177
    +0.10
    0.5%
    217
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.10
    0.03
    133
    +0.10
    0.03
    111
    +0.10
    0.03
    Negative Logits
    adas
    -0.93
    milo
    -0.89
    aley
    -0.86
    gdala
    -0.83
    anners
    -0.78
    kk
    -0.77
    (),
    -0.76
    ι
    -0.76
    inka
    -0.75
    iliated
    -0.75
    POSITIVE LOGITS
     Must
    0.77
    etsu
    0.75
     acknow
    0.73
     Article
    0.72
     ex
    0.71
     tooth
    0.71
     peace
    0.70
    Must
    0.69
     ie
    0.69
     Know
    0.68
    Activations Density 0.179%

    No Known Activations