© 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. 7941
    Prev
    Next
    INDEX
    Explanations

    locations in a city

    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
    238
    +0.09
    0.4%
    765
    +0.09
    0.4%
    590
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.09
    0.04
    471
    +0.09
    0.04
    269
    +0.09
    0.04
    Negative Logits
    acters
    -0.72
    APP
    -0.66
    DragonMagazine
    -0.65
    otle
    -0.65
    amount
    -0.65
    mails
    -0.64
     cruc
    -0.62
    Age
    -0.61
    Apps
    -0.60
    anders
    -0.60
    POSITIVE LOGITS
     behalf
    1.28
    etime
    1.13
     weekends
    1.07
     Sundays
    1.03
    shore
    1.01
     Saturdays
    0.98
     campus
    0.96
    yx
    0.94
     Canal
    0.94
     Fridays
    0.93
    Activations Density 0.125%

    No Known Activations