© 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. 5397
    Prev
    Next
    INDEX
    Explanations

    words related to international politics and conflicts

    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
    655
    +0.12
    0.6%
    679
    +0.12
    0.5%
    150
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.12
    0.09
    109
    +0.12
    0.07
    551
    +0.09
    0.06
    Negative Logits
     sounding
    -0.67
     guessing
    -0.66
    âĨ
    -0.64
     Anyway
    -0.62
    hatt
    -0.60
     Riding
    -0.59
     Landing
    -0.58
     ðŁĺ
    -0.57
    DI
    -0.57
     Interesting
    -0.56
    POSITIVE LOGITS
     currently
    0.97
     formerly
    0.93
     resulted
    0.92
     spans
    0.91
     comprise
    0.89
    currently
    0.88
     culminated
    0.88
     threatens
    0.88
     oversees
    0.87
     traditionally
    0.86
    Activations Density 0.237%

    No Known Activations