© 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. 3667
    Prev
    Next
    INDEX
    Explanations

    names of sports players, directors, writers, and cast members

    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
    659
    +0.17
    0.9%
    365
    +0.10
    0.5%
    176
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.17
    0.11
    232
    +0.10
    0.07
    511
    +0.09
    0.05
    Negative Logits
     seriously
    -0.57
     Emblem
    -0.56
     envy
    -0.55
     Narendra
    -0.54
     Millennials
    -0.54
     millennials
    -0.54
    ãĤ°
    -0.53
     online
    -0.52
     stubborn
    -0.52
     Naruto
    -0.51
    POSITIVE LOGITS
    icz
    0.98
    onson
    0.94
    cko
    0.93
    kson
    0.93
    anson
    0.93
    inski
    0.92
    antz
    0.91
    anski
    0.91
    eson
    0.90
    zinski
    0.90
    Activations Density 0.228%

    No Known Activations