© 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 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. 12379
    Prev
    Next
    INDEX
    Explanations

    word combinations related to sports competitions and qualifications

    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
    93
    +0.11
    0.5%
    268
    +0.11
    0.5%
    500
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.11
    0.04
    500
    +0.11
    0.04
    24
    +0.11
    0.03
    Negative Logits
    imaru
    -0.79
    arre
    -0.78
    argon
    -0.76
     Anon
    -0.76
    kinson
    -0.73
    hart
    -0.72
    natureconservancy
    -0.72
    onica
    -0.70
    enegger
    -0.70
    nu
    -0.70
    POSITIVE LOGITS
     semifinals
    1.22
     finals
    1.22
     playoffs
    1.17
     standings
    1.16
     elimination
    1.09
     relegation
    1.07
    finals
    1.07
     playoff
    1.06
     finalists
    1.06
     winners
    1.03
    Activations Density 0.139%

    No Known Activations