© 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 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. 18058
    Prev
    Next
    INDEX
    Explanations

    years or dates

    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
    35
    +0.14
    0.7%
    314
    +0.12
    0.6%
    183
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.14
    0.04
    35
    +0.12
    0.04
    693
    +0.12
    0.04
    Negative Logits
    plom
    -0.78
    pora
    -0.73
    afort
    -0.69
    hei
    -0.68
    henko
    -0.66
    ño
    -0.65
    ablo
    -0.64
    ãĥ£
    -0.62
    kell
    -0.61
    osal
    -0.61
    POSITIVE LOGITS
    âĸĪâĸĪ
    1.05
    th
    0.92
    committee
    0.90
    skirts
    0.87
    ISH
    0.85
    200000
    0.81
    %"
    0.81
    isher
    0.81
    61
    0.80
    %
    0.80
    Activations Density 0.064%

    No Known Activations