© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25936
    Prev
    Next
    INDEX
    Explanations

    terms related to lobbying and influence in political contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    321
    +0.10
    0.5%
    496
    +0.10
    0.4%
    642
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.10
    0.01
    70
    +0.10
    0.02
    282
    +0.10
    0.01
    Negative Logits
     rapp
    -0.74
    dylib
    -0.70
    ãĤ©
    -0.66
    nings
    -0.63
    è¯
    -0.61
     Loaded
    -0.61
     Dresden
    -0.61
     Syndrome
    -0.61
     sarc
    -0.61
    ãĥł
    -0.60
    POSITIVE LOGITS
     against
    1.07
     policymakers
    0.98
     tirelessly
    0.93
     electors
    0.91
     legislators
    0.89
     furiously
    0.88
     vigorously
    0.87
     unsuccessfully
    0.86
     vehemently
    0.82
     extensively
    0.82
    Activations Density 0.033%

    No Known Activations