© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16783
    Prev
    Next
    INDEX
    Explanations

    phrases indicating sharing personal experiences or opinions

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    638
    +0.12
    0.5%
    380
    +0.11
    0.5%
    588
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.12
    0.03
    638
    +0.11
    0.03
    713
    +0.10
    0.03
    Negative Logits
    azaar
    -0.65
    AFTA
    -0.65
    enta
    -0.65
    iyah
    -0.63
    tyard
    -0.63
     Responsibility
    -0.63
    anamo
    -0.62
    geoning
    -0.62
    aund
    -0.61
    phe
    -0.61
    POSITIVE LOGITS
     fuss
    0.78
     trending
    0.75
     differe
    0.66
     pans
    0.66
     fit
    0.65
     agre
    0.65
     cracks
    0.64
     chops
    0.64
     trends
    0.63
     shenanigans
    0.62
    Activations Density 0.154%

    No Known Activations