© 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. 26730
    Prev
    Next
    INDEX
    Explanations

    references to elections and related political terms

    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
    288
    +0.15
    0.7%
    538
    +0.10
    0.5%
    531
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    531
    +0.15
    0.01
    538
    +0.10
    0.01
    35
    +0.10
    0.01
    Negative Logits
    pots
    -0.86
    resp
    -0.85
    Origin
    -0.80
    erk
    -0.80
    sf
    -0.79
    cius
    -0.77
    orld
    -0.74
    erd
    -0.74
    eric
    -0.73
    edin
    -0.72
    POSITIVE LOGITS
     elections
    1.32
     election
    1.19
     electorate
    1.07
     Election
    1.05
     reelection
    1.01
     Elections
    0.99
     midterm
    0.97
     polls
    0.91
     voting
    0.90
     ballot
    0.87
    Activations Density 0.004%

    No Known Activations