© 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. 4511
    Prev
    Next
    INDEX
    Explanations

    information about books, publications, and articles

    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
    641
    +0.10
    0.4%
    220
    +0.09
    0.4%
    583
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.10
    0.04
    641
    +0.09
    0.04
    231
    +0.09
    0.04
    Negative Logits
    itiz
    -0.79
     crawl
    -0.61
     forg
    -0.60
    zona
    -0.59
    chenko
    -0.59
     helicop
    -0.57
     jaws
    -0.56
     looms
    -0.56
    adr
    -0.56
     eh
    -0.56
    POSITIVE LOGITS
    bidden
    1.55
    gotten
    1.52
    ced
    1.24
    give
    1.16
    cing
    1.15
     example
    1.12
    wards
    1.11
    bes
    1.09
     instance
    1.03
    getting
    1.03
    Activations Density 0.054%

    No Known Activations