© 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 1536
    9. 8-RES_FS1536-JB
    11. 1144
    Prev
    Next
    INDEX
    Explanations

    references to business and financial information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    669
    +0.11
    0.5%
    88
    +0.09
    0.4%
    589
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.11
    0.08
    608
    +0.09
    0.09
    88
    +0.09
    0.06
    Negative Logits
    ANS
    -0.96
    ans
    -0.74
     Cosponsors
    -0.73
    fell
    -0.73
    ornia
    -0.71
    CCC
    -0.70
    assian
    -0.69
    iste
    -0.69
    mid
    -0.68
    iland
    -0.68
    POSITIVE LOGITS
     being
    0.87
     providing
    0.79
     complying
    0.75
     anecdotal
    0.72
     saving
    0.72
     ensuring
    0.72
     occasional
    0.72
     protecting
    0.71
     having
    0.70
     basics
    0.70
    Activations Density 1.503%

    No Known Activations