© 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. 3248
    Prev
    Next
    INDEX
    Explanations

    references to various specific topics including fairy tales, messes, foreign policy, specific models of iPhones, political parties, individuals, and specific events like St. Patrick's Day

    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
    87
    +0.19
    0.9%
    52
    +0.11
    0.5%
    459
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.09
    711
    +0.11
    0.04
    67
    +0.11
    0.06
    Negative Logits
    ĸļ
    -0.86
     Shutterstock
    -0.66
     Sturgeon
    -0.65
    epad
    -0.60
    leneck
    -0.60
    ouf
    -0.58
     Hague
    -0.56
    ité
    -0.56
     Kejriwal
    -0.56
     Profile
    -0.56
    POSITIVE LOGITS
     equivalents
    0.99
     variants
    0.97
     varieties
    0.95
     clones
    0.95
     entries
    0.94
    isations
    0.92
     iterations
    0.91
     instances
    0.88
     slots
    0.87
    doms
    0.86
    Activations Density 0.790%

    No Known Activations