© 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. 22833
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals and places

    oai_token-act-pair · gpt-4o-miniTriggered 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
    314
    +0.19
    0.9%
    659
    +0.12
    0.5%
    597
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.19
    0.12
    314
    +0.12
    0.02
    145
    +0.10
    0.07
    Negative Logits
     Rebellion
    -0.73
     Leviathan
    -0.73
     Cerberus
    -0.71
     Colleges
    -0.68
     theaters
    -0.67
     downgrade
    -0.66
     Rebels
    -0.65
     Wonderland
    -0.65
     reminders
    -0.65
     machines
    -0.65
    POSITIVE LOGITS
    ileen
    1.08
    ona
    1.08
    aryl
    1.06
    ergus
    1.06
    frey
    1.05
    ilyn
    1.04
    ureen
    1.04
    annie
    1.03
    jan
    1.03
    berto
    1.03
    Activations Density 0.391%

    No Known Activations