© 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. 8760
    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
    132
    +0.13
    0.6%
    587
    +0.11
    0.5%
    29
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.01
    659
    +0.11
    0.01
    29
    +0.10
    0.01
    Negative Logits
    minist
    -0.78
    女
    -0.77
    asted
    -0.73
    ebin
    -0.71
     secretaries
    -0.70
    è¦ļéĨĴ
    -0.70
    atu
    -0.69
    omething
    -0.68
    ratulations
    -0.67
    cffff
    -0.67
    POSITIVE LOGITS
     Ventura
    0.99
     Owens
    0.88
     Pink
    0.83
    Serv
    0.80
    clair
    0.77
     Eisen
    0.76
    lyn
    0.76
    Lens
    0.74
     Liver
    0.73
     Sanchez
    0.73
    Activations Density 0.020%

    No Known Activations