© 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. 16362
    Prev
    Next
    INDEX
    Explanations

    news related to politics and legal matters, such as deals made by politicians, court rulings, and government actions

    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
    480
    +0.59
    3.4%
    87
    +0.19
    1.1%
    266
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.59
    0.04
    266
    +0.19
    0.11
    199
    +0.17
    0.09
    Negative Logits
     anecd
    -0.68
    retty
    -0.62
    udos
    -0.54
    eday
    -0.52
     nep
    -0.50
    Production
    -0.49
    Apply
    -0.49
     "%
    -0.48
    AAAAAAAA
    -0.47
    TPPStreamerBot
    -0.47
    POSITIVE LOGITS
     uprising
    0.56
    Ħ¢
    0.56
     apartheid
    0.54
     blight
    0.53
    addafi
    0.52
     ÂŃ
    0.52
    Merit
    0.51
     massacre
    0.51
     communism
    0.51
     bombings
    0.50
    Activations Density 1.455%

    No Known Activations