© 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. 15620
    Prev
    Next
    INDEX
    Explanations

    phrases related to jokes

    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
    447
    +0.13
    0.6%
    132
    +0.12
    0.5%
    267
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    340
    +0.13
    0.02
    132
    +0.12
    0.02
    568
    +0.12
    0.02
    Negative Logits
    undai
    -0.78
    ignty
    -0.75
    ills
    -0.70
    phalt
    -0.69
    ignt
    -0.66
    enture
    -0.66
    metics
    -0.66
    EVA
    -0.66
    emale
    -0.66
    20439
    -0.65
    POSITIVE LOGITS
    ously
    1.08
     jokes
    0.97
     joking
    0.89
     mocking
    0.84
     joke
    0.83
    bag
    0.82
    sters
    0.80
    enegger
    0.80
    ster
    0.78
    bags
    0.78
    Activations Density 0.025%

    No Known Activations