© 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. 14265
    Prev
    Next
    INDEX
    Explanations

    Slavic languages with diacritics as well as specific names and abbreviations in Slavic culture

    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
    481
    +0.15
    0.7%
    614
    +0.11
    0.5%
    758
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.15
    0.04
    659
    +0.11
    0.03
    180
    +0.10
    0.02
    Negative Logits
     adolesc
    -0.97
     IM
    -0.80
     Reed
    -0.76
     4090
    -0.71
     OL
    -0.71
     LI
    -0.71
     IMF
    -0.70
     Zup
    -0.68
     Io
    -0.68
     MTA
    -0.67
    POSITIVE LOGITS
    ch
    1.44
    chu
    1.43
    cha
    1.31
    Ch
    1.20
    och
    1.17
    chy
    1.16
    cho
    1.15
    cht
    1.14
    CH
    1.13
    ech
    1.13
    Activations Density 0.137%

    No Known Activations