© 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. 14587
    Prev
    Next
    INDEX
    Explanations

    details related to international trade agreements and government policies

    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
    +0.53
    2.8%
    266
    +0.16
    0.9%
    87
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.53
    0.02
    266
    +0.16
    0.09
    561
    +0.12
    0.06
    Negative Logits
    ////////////////
    -0.58
    oooooooooooooooo
    -0.57
    orem
    -0.56
    pure
    -0.56
    velt
    -0.54
    teenth
    -0.54
    illac
    -0.53
    Anyway
    -0.53
    gment
    -0.52
    Excellent
    -0.52
    POSITIVE LOGITS
     watchdog
    0.87
     lawmakers
    0.80
     campaigners
    0.75
     regulators
    0.74
     crackdown
    0.73
     fears
    0.71
     embattled
    0.71
    Reuters
    0.70
     prosecutors
    0.69
     leaked
    0.69
    Activations Density 1.012%

    No Known Activations