© 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 49152
    9. 8-RES_FS49152-JB
    11. 37590
    Prev
    Next
    INDEX
    Explanations

    terms associated with various types of sports, particularly football and related institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    480
    +0.48
    2.5%
    266
    +0.11
    0.6%
    110
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.48
    0.09
    110
    +0.11
    0.06
    575
    +0.11
    0.07
    Negative Logits
     oneself
    -0.73
    uador
    -0.72
    akespeare
    -0.62
     Anon
    -0.62
    skirts
    -0.62
    rupulous
    -0.61
    ocent
    -0.59
    icans
    -0.58
    flix
    -0.58
    unin
    -0.56
    POSITIVE LOGITS
     division
    0.95
     program
    0.88
     counterpart
    0.88
     arsenal
    0.86
     portfolio
    0.86
     programme
    0.86
     counterparts
    0.84
     holdings
    0.84
     empire
    0.82
     lineup
    0.81
    Activations Density 0.432%

    No Known Activations