© 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. 20635
    Prev
    Next
    INDEX
    Explanations

    text related to cooperative game theory and decision-making

    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
    87
    +0.31
    1.6%
    756
    +0.18
    0.9%
    570
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.31
    0.04
    756
    +0.18
    -0.01
    87
    +0.11
    -0.02
    Negative Logits
     acron
    -0.77
    soDeliveryDate
    -0.68
     Journalism
    -0.66
    Weather
    -0.66
    audi
    -0.62
     journalism
    -0.59
     Inspector
    -0.59
     Canaver
    -0.58
    Politics
    -0.57
    cour
    -0.57
    POSITIVE LOGITS
     corresponding
    0.86
     subsequent
    0.85
     versa
    0.79
     adjacent
    0.78
     unchanged
    0.75
     remainder
    0.74
     downstream
    0.73
     unus
    0.71
     subtract
    0.69
     minus
    0.69
    Activations Density 0.909%

    No Known Activations