© 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. 22162
    Prev
    Next
    INDEX
    Explanations

    references to fights and boxing events

    oai_token-act-pair · gpt-4o-miniTriggered 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
    749
    +0.10
    0.5%
    247
    +0.10
    0.5%
    708
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.10
    0.02
    85
    +0.10
    0.02
    492
    +0.10
    0.02
    Negative Logits
    ridges
    -0.73
    ocument
    -0.72
    asper
    -0.72
    essage
    -0.72
    Ire
    -0.71
    GES
    -0.68
    quist
    -0.67
    uyomi
    -0.67
    pex
    -0.66
    conservancy
    -0.66
    POSITIVE LOGITS
     promoter
    0.81
     against
    0.78
    match
    0.75
     rematch
    0.75
     stopp
    0.73
     chore
    0.72
     bouts
    0.71
     unbeaten
    0.70
    card
    0.69
     bout
    0.69
    Activations Density 0.039%

    No Known Activations