© 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. 1508
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions

    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
    480
    +0.41
    2.2%
    447
    +0.31
    1.7%
    87
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.41
    0.10
    480
    +0.31
    0.03
    739
    +0.14
    0.04
    Negative Logits
     enthusi
    -0.56
    luster
    -0.52
    ãĥ¼ãĥĨ
    -0.52
     Vaugh
    -0.51
    Mobil
    -0.50
    anwhile
    -0.50
    interstitial
    -0.50
    sit
    -0.49
    rouse
    -0.48
     wealthier
    -0.46
    POSITIVE LOGITS
    É
    0.78
    [/
    0.77
    ãĢij
    0.73
    \":
    0.69
    ¨
    0.69
     âĢº
    0.66
     ãģ
    0.65
     [/
    0.64
     âĻ
    0.63
    %"
    0.63
    Activations Density 1.311%

    No Known Activations