© 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. 45686
    Prev
    Next
    INDEX
    Explanations

    references to politicians and political figures

    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
    +0.13
    0.6%
    447
    +0.13
    0.6%
    679
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.13
    0.02
    325
    +0.13
    0.02
    254
    +0.13
    0.02
    Negative Logits
    actory
    -0.73
    uras
    -0.68
    ļé
    -0.65
    awar
    -0.64
     Condition
    -0.64
     Infinite
    -0.64
     Width
    -0.64
    ventory
    -0.64
    wered
    -0.64
     Resurrection
    -0.63
    POSITIVE LOGITS
    clinton
    1.08
    hips
    0.91
    hip
    0.84
    icians
    0.80
     appoint
    0.80
    woman
    0.74
    makers
    0.73
     correctness
    0.72
     elected
    0.72
     Franch
    0.69
    Activations Density 0.019%

    No Known Activations