© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 10549
    Prev
    Next
    INDEX
    Explanations

    references to international travel and political meetings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    608
    +0.13
    0.6%
    290
    +0.10
    0.4%
    420
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.13
    0.08
    665
    +0.10
    0.06
    104
    +0.10
    0.05
    Negative Logits
    anni
    -0.69
     ticking
    -0.68
    achy
    -0.68
    standing
    -0.68
    going
    -0.68
    rated
    -0.64
     transmitted
    -0.64
    runner
    -0.63
    unn
    -0.63
     hurled
    -0.63
    POSITIVE LOGITS
     Disneyland
    0.94
     meet
    0.94
     Wonderland
    0.88
     Dover
    0.87
     Vegas
    0.84
     India
    0.83
     Asheville
    0.82
     Osaka
    0.82
     Rome
    0.81
     Prague
    0.81
    Activations Density 0.270%

    No Known Activations