© 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. 3153
    Prev
    Next
    INDEX
    Explanations

    words related to specific TV shows and series

    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
    447
    +0.26
    1.2%
    481
    +0.14
    0.7%
    359
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.26
    0.06
    667
    +0.14
    0.05
    326
    +0.10
    0.04
    Negative Logits
    hiba
    -0.80
     pump
    -0.78
     confer
    -0.72
    sembly
    -0.71
     regulated
    -0.71
     fiat
    -0.71
     offic
    -0.69
     regulator
    -0.68
     distingu
    -0.68
    soType
    -0.67
    POSITIVE LOGITS
     Chronicles
    1.06
     sequel
    0.93
     Odyssey
    0.92
     Season
    0.92
     Adventure
    0.91
     trilogy
    0.90
     Fever
    0.89
     Resurrection
    0.89
    Fest
    0.88
     Trilogy
    0.88
    Activations Density 0.239%

    No Known Activations