© 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. 16172
    Prev
    Next
    INDEX
    Explanations

    names of sports teams and related events

    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
    202
    +0.13
    0.6%
    577
    +0.10
    0.4%
    548
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.13
    0.04
    548
    +0.10
    0.03
    577
    +0.09
    0.03
    Negative Logits
    schild
    -1.02
    chwitz
    -0.89
    enegger
    -0.81
    ĸļ
    -0.75
     Shant
    -0.75
     Shutterstock
    -0.75
    staking
    -0.74
    é¾įå¥ij士
    -0.73
     Duterte
    -0.72
     relativity
    -0.71
    POSITIVE LOGITS
     Falcons
    1.07
     Panthers
    1.06
     Devils
    1.05
    hawks
    1.04
    birds
    1.04
     Bulldogs
    1.03
     Tigers
    1.01
     Wolves
    1.00
     Bucs
    1.00
     Eagles
    0.99
    Activations Density 0.182%

    No Known Activations