© 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 24576
    9. 8-RES_FS24576-JB
    11. 8498
    Prev
    Next
    INDEX
    Explanations

    soccer teams

    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
    288
    +0.09
    0.4%
    373
    +0.09
    0.4%
    578
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.09
    0.02
    220
    +0.09
    0.02
    112
    +0.09
    0.02
    Negative Logits
    lihood
    -0.84
    Downloadha
    -0.75
    bilt
    -0.71
     Ples
    -0.69
    bringer
    -0.65
    beit
    -0.62
    mond
    -0.62
     Schwarzenegger
    -0.61
     Alibaba
    -0.61
    ysis
    -0.61
    POSITIVE LOGITS
     Cincinnati
    0.81
    ORE
    0.81
    RIC
    0.78
    soc
    0.78
    erning
    0.77
    ocused
    0.74
    FC
    0.74
     Wim
    0.73
    VII
    0.72
    ilage
    0.72
    Activations Density 0.018%

    No Known Activations