© 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. 5431
    Prev
    Next
    INDEX
    Explanations

    humorous content, specifically jokes and humor

    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
    151
    +0.14
    0.7%
    288
    +0.12
    0.6%
    255
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.14
    0.02
    288
    +0.12
    0.02
    255
    +0.11
    0.02
    Negative Logits
    holder
    -0.69
     eyed
    -0.62
    arnaev
    -0.60
     Kuh
    -0.60
    ports
    -0.58
     AVG
    -0.57
    ignty
    -0.57
     territories
    -0.56
    FT
    -0.55
     braking
    -0.55
    POSITIVE LOGITS
    ously
    1.39
    osity
    0.99
    ous
    0.90
    aceous
    0.90
    atur
    0.86
    isms
    0.86
    netflix
    0.86
    isma
    0.85
    lessness
    0.83
    fulness
    0.82
    Activations Density 0.045%

    No Known Activations