© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14828
    Prev
    Next
    INDEX
    Explanations

    numerical information or figures related to estimates and quantities

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    730
    +0.11
    0.5%
    465
    +0.10
    0.4%
    14
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.11
    0.02
    730
    +0.10
    0.05
    512
    +0.10
    0.05
    Negative Logits
    æ©Ł
    -0.69
    baugh
    -0.69
    reetings
    -0.66
    Problem
    -0.64
    malink
    -0.64
    folio
    -0.62
     Statement
    -0.62
    igue
    -0.62
    udeb
    -0.62
    ":{"
    -0.61
    POSITIVE LOGITS
     even
    1.19
     downright
    1.02
     outright
    0.91
    even
    0.82
     hundreds
    0.81
    undreds
    0.79
     entire
    0.77
    yond
    0.73
     EVEN
    0.72
     amput
    0.71
    Activations Density 0.818%

    No Known Activations