© 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. 14741
    Prev
    Next
    INDEX
    Explanations

    ingredients and recipes for specific dishes, such as cheesecake and apple crumble

    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
    232
    +0.10
    0.4%
    260
    +0.09
    0.4%
    374
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.04
    232
    +0.09
    0.04
    343
    +0.09
    0.03
    Negative Logits
     seism
    -0.92
     regress
    -0.83
     exile
    -0.77
     geographically
    -0.77
     notor
    -0.76
     proced
    -0.76
    alysed
    -0.76
     sciences
    -0.75
     observers
    -0.75
     strateg
    -0.75
    POSITIVE LOGITS
     Cream
    1.32
     Sauce
    1.29
     Cups
    1.24
     Powder
    1.23
     Cake
    1.23
     Cheese
    1.23
     Recipe
    1.21
     Salad
    1.20
     Breast
    1.19
     Blend
    1.17
    Activations Density 0.165%

    No Known Activations