© 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. 3069
    Prev
    Next
    INDEX
    Explanations

    dates expressed in numerical form

    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
    373
    +0.17
    0.8%
    345
    +0.11
    0.5%
    717
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.17
    -0.01
    6
    +0.11
    0.03
    739
    +0.10
    0.01
    Negative Logits
    auga
    -0.69
     plots
    -0.67
    ault
    -0.62
    ieg
    -0.61
    antis
    -0.61
    ief
    -0.61
    uces
    -0.60
    icter
    -0.58
    inqu
    -0.58
    arkin
    -0.58
    POSITIVE LOGITS
    quickShipAvailable
    0.93
    UTC
    0.71
     UTC
    0.69
     PST
    0.66
     04
    0.66
     RELEASE
    0.65
     REUTERS
    0.64
    ãĥŁ
    0.64
     08
    0.63
     GMT
    0.61
    Activations Density 0.065%

    No Known Activations