© 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. 3902
    Prev
    Next
    INDEX
    Explanations

    statements related to political issues or debates

    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
    627
    +0.14
    0.7%
    592
    +0.12
    0.6%
    476
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.14
    0.03
    627
    +0.12
    0.02
    530
    +0.12
    0.02
    Negative Logits
    yip
    -0.83
    esville
    -0.74
    76561
    -0.74
    bole
    -0.74
    Answer
    -0.69
    isance
    -0.68
    ndum
    -0.67
    milo
    -0.67
    ua
    -0.67
    utra
    -0.66
    POSITIVE LOGITS
     Variant
    0.86
     Valiant
    0.84
     Whedon
    0.77
    Cover
    0.76
     Hirosh
    0.76
    Writer
    0.76
    redits
    0.75
    eatures
    0.74
     Warlock
    0.72
     COVER
    0.71
    Activations Density 0.090%

    No Known Activations