© 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. 15329
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "Kosher"

    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
    695
    +0.11
    0.5%
    48
    +0.11
    0.5%
    191
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.04
    326
    +0.11
    0.03
    645
    +0.11
    0.03
    Negative Logits
    IBLE
    -0.83
    ãĥ¼ãĥĨãĤ£
    -0.76
    iments
    -0.76
    ional
    -0.68
    Charge
    -0.67
    Ö¼
    -0.66
    EMENT
    -0.64
    ions
    -0.64
    天
    -0.62
    phrine
    -0.62
    POSITIVE LOGITS
    lov
    0.87
     Klux
    0.85
    lyak
    0.84
    won
    0.82
    inski
    0.79
    etchup
    0.76
    lein
    0.76
    mare
    0.76
    ernels
    0.75
    ernel
    0.74
    Activations Density 0.062%

    No Known Activations