© 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. 2814
    Prev
    Next
    INDEX
    Explanations

    references to sports teams or players, specifically focusing on the team "Badgers."

    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
    0
    +0.12
    0.6%
    608
    +0.11
    0.5%
    584
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    +0.12
    0.01
    211
    +0.11
    0.01
    357
    +0.10
    0.01
    Negative Logits
    ĸļ
    -0.88
    conservancy
    -0.85
    izabeth
    -0.78
    theless
    -0.71
    orthy
    -0.71
    plete
    -0.69
    thens
    -0.68
    accompan
    -0.68
    utical
    -0.68
     helic
    -0.67
    POSITIVE LOGITS
    ger
    1.20
    ges
    1.12
    gers
    1.06
    die
    1.00
    ged
    1.00
    ging
    0.92
    ass
    0.90
    ge
    0.88
    lands
    0.85
    Bad
    0.83
    Activations Density 0.010%

    No Known Activations