© 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. 4897
    Prev
    Next
    INDEX
    Explanations

    references to GitHub repositories, updates, and tutorials

    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
    294
    +0.13
    0.6%
    385
    +0.12
    0.5%
    508
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.13
    0.01
    500
    +0.12
    0.01
    294
    +0.12
    0.01
    Negative Logits
    ewitness
    -0.76
    estinal
    -0.76
    iscons
    -0.71
    phe
    -0.70
    ecause
    -0.70
    atonin
    -0.69
    xon
    -0.68
    IU
    -0.67
    undai
    -0.67
    ccording
    -0.66
    POSITIVE LOGITS
     repositories
    1.07
     repository
    1.07
     Pages
    0.99
     repo
    0.97
    usercontent
    0.93
     Commons
    0.77
     Contribut
    0.75
     GitHub
    0.75
    docs
    0.74
    ãĤĮ
    0.73
    Activations Density 0.017%

    No Known Activations