© 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 12288
    9. 8-RES_FS12288-JB
    11. 1573
    Prev
    Next
    INDEX
    Explanations

    statements related to plans or commitments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    481
    +0.12
    0.6%
    420
    +0.11
    0.5%
    718
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.12
    0.07
    718
    +0.11
    0.06
    139
    +0.11
    0.06
    Negative Logits
    aukee
    -0.77
    Skip
    -0.66
    ãĤ´ãĥ³
    -0.66
     Previous
    -0.64
     Distance
    -0.63
    icist
    -0.63
    ĨĴ
    -0.61
     Elias
    -0.61
     Nelson
    -0.60
     Electrical
    -0.60
    POSITIVE LOGITS
     consequently
    1.20
    'll
    1.18
     accordingly
    1.15
     certainly
    1.05
     therefore
    1.04
    're
    0.93
    've
    0.93
     shouldn
    0.91
     deserve
    0.91
     hereby
    0.87
    Activations Density 0.309%

    No Known Activations