© 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. 3628
    Prev
    Next
    INDEX
    Explanations

    locations or orientations related to the front or back

    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
    191
    +0.11
    0.5%
    459
    +0.10
    0.4%
    607
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.11
    0.04
    607
    +0.10
    0.04
    571
    +0.10
    0.04
    Negative Logits
    edIn
    -0.73
     Parenthood
    -0.73
    upon
    -0.69
    ensable
    -0.67
    enegger
    -0.66
    ategor
    -0.65
     Cosponsors
    -0.64
    artisan
    -0.64
    isen
    -0.64
    DCS
    -0.63
    POSITIVE LOGITS
     of
    1.02
     thereof
    0.94
    most
    0.91
     porch
    0.87
     pane
    0.84
    boards
    0.83
     window
    0.81
     pedest
    0.81
     corner
    0.80
     door
    0.80
    Activations Density 0.127%

    No Known Activations