© 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 24576
    9. 8-RES_FS24576-JB
    11. 18422
    Prev
    Next
    INDEX
    Explanations

    vehicle-related terms

    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
    346
    +0.13
    0.6%
    425
    +0.09
    0.4%
    459
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    652
    +0.13
    0.05
    346
    +0.09
    0.04
    537
    +0.09
    0.04
    Negative Logits
     Flavoring
    -0.81
     Seym
    -0.75
    ãĤ´ãĥ³
    -0.72
    ettings
    -0.70
    reality
    -0.69
    uden
    -0.68
    utical
    -0.67
    maxwell
    -0.66
     Pinball
    -0.66
    xp
    -0.65
    POSITIVE LOGITS
     parked
    1.21
     transporting
    0.98
    load
    0.94
    wagon
    0.94
     towed
    0.93
     SUV
    0.92
     carrying
    0.92
     crashed
    0.91
    loads
    0.90
     convoy
    0.89
    Activations Density 0.094%

    No Known Activations