© 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. 45804
    Prev
    Next
    INDEX
    Explanations

    references to sports leagues, rankings, and performance metrics

    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
    422
    +0.10
    0.4%
    16
    +0.09
    0.4%
    50
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.10
    0.03
    575
    +0.09
    0.04
    312
    +0.09
    0.02
    Negative Logits
    ollah
    -0.71
    ban
    -0.69
    cop
    -0.66
     contaminated
    -0.65
     miscon
    -0.65
    infect
    -0.64
     Fukushima
    -0.64
    nect
    -0.62
     disillusion
    -0.62
     reconnect
    -0.62
    POSITIVE LOGITS
     standings
    1.31
     rankings
    1.30
     Rankings
    1.10
     category
    0.99
     ranking
    0.92
     classification
    0.91
     categories
    0.85
     scoring
    0.85
    Statistics
    0.84
     Ranking
    0.82
    Activations Density 0.173%

    No Known Activations