© 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. 18694
    Prev
    Next
    INDEX
    Explanations

    statistical and numerical information, including counts and rates

    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
    447
    +0.13
    0.6%
    260
    +0.12
    0.6%
    95
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.13
    0.05
    260
    +0.12
    0.05
    545
    +0.11
    0.04
    Negative Logits
    rum
    -0.67
    rology
    -0.62
    eston
    -0.56
     Mahar
    -0.56
    activ
    -0.54
     Fol
    -0.54
    SPONSORED
    -0.53
     Slater
    -0.52
     Greene
    -0.52
    oid
    -0.51
    POSITIVE LOGITS
     apiece
    1.82
    poons
    1.38
     per
    1.28
     consecut
    0.97
    paces
    0.93
     increments
    0.92
     each
    0.91
    each
    0.89
    poon
    0.87
     total
    0.86
    Activations Density 0.237%

    No Known Activations