© 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. 8714
    Prev
    Next
    INDEX
    Explanations

    expressions of doubt or uncertainty

    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
    659
    +0.10
    0.5%
    510
    +0.10
    0.4%
    243
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    431
    +0.10
    0.03
    243
    +0.10
    0.03
    510
    +0.10
    0.03
    Negative Logits
    etheus
    -0.76
    SPONSORED
    -0.74
    orthy
    -0.73
    merce
    -0.70
     Âł Âł
    -0.69
    anwhile
    -0.66
     undet
    -0.64
    eki
    -0.63
    aneously
    -0.61
    Result
    -0.61
    POSITIVE LOGITS
    soType
    0.69
     passionate
    0.69
    )</
    0.67
     sometimes
    0.65
     cried
    0.65
     cliché
    0.64
     someday
    0.64
     firsthand
    0.63
     sarcastic
    0.62
     sarc
    0.62
    Activations Density 0.190%

    No Known Activations