© 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 24576
    9. 8-RES_FS24576-JB
    11. 8563
    Prev
    Next
    INDEX
    Explanations

    people's names

    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
    721
    +0.14
    0.6%
    48
    +0.12
    0.6%
    201
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.14
    0.01
    201
    +0.12
    0.01
    232
    +0.12
    0.01
    Negative Logits
    uyomi
    -0.70
     guiActiveUnfocused
    -0.70
     Gemini
    -0.69
    代
    -0.69
     hardened
    -0.67
     digits
    -0.64
     Mayhem
    -0.63
     Ceres
    -0.63
     multiplication
    -0.62
     Mirror
    -0.62
    POSITIVE LOGITS
    keye
    1.77
    keyes
    1.46
    aii
    1.32
    orth
    1.22
    kes
    1.09
    haw
    1.08
    ield
    1.06
    kward
    1.03
    ijah
    1.02
    igan
    0.97
    Activations Density 0.013%

    No Known Activations