© 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 EvalsExportsinterp-engineNEWAPI 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. 16050
    Prev
    Next
    INDEX
    Explanations

    mentions of political events, particularly regarding an election and its aftermath

    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
    288
    +0.14
    0.6%
    44
    +0.12
    0.5%
    666
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    666
    +0.14
    0.04
    499
    +0.12
    0.03
    350
    +0.10
    0.03
    Negative Logits
    krit
    -0.76
    ciplinary
    -0.75
    DEP
    -0.74
     Flavoring
    -0.71
    ynt
    -0.71
    ĸļ
    -0.71
    SourceFile
    -0.71
    pread
    -0.70
    ournals
    -0.69
    inks
    -0.68
    POSITIVE LOGITS
    eering
    1.50
     cycle
    0.98
     campaign
    0.98
     campaigns
    0.96
     defeat
    0.90
     season
    0.90
     outcome
    0.83
     turnout
    0.81
     election
    0.81
     loser
    0.80
    Activations Density 0.038%

    No Known Activations