© 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 EvalsExportsinterp-engineNEWAPI 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. 13341
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms and 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_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
    397
    +0.11
    0.5%
    194
    +0.10
    0.5%
    566
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    366
    +0.11
    0.03
    397
    +0.10
    0.03
    194
    +0.10
    0.03
    Negative Logits
    idth
    -0.70
     hello
    -0.68
     Legislature
    -0.61
    iesta
    -0.60
    ustration
    -0.60
     Words
    -0.59
    inav
    -0.59
    eties
    -0.57
    how
    -0.56
     Anger
    -0.56
    POSITIVE LOGITS
     unsu
    1.08
     susceptible
    1.01
     unus
    0.97
     ineligible
    0.90
     unfit
    0.88
     vulnerable
    0.88
     unlikely
    0.86
     easier
    0.84
     eligible
    0.83
     ripe
    0.83
    Activations Density 0.084%

    No Known Activations