© 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 24576
    9. 8-RES_FS24576-JB
    11. 9902
    Prev
    Next
    INDEX
    Explanations

    words related to political leadership and movements

    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
    253
    +0.12
    0.5%
    496
    +0.11
    0.5%
    642
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.12
    0.02
    232
    +0.11
    0.02
    701
    +0.10
    0.01
    Negative Logits
    bush
    -0.64
     Amnesty
    -0.62
     embell
    -0.62
     todd
    -0.59
     mileage
    -0.58
     scraping
    -0.57
    acting
    -0.56
    vas
    -0.56
    yright
    -0.55
     Lemon
    -0.54
    POSITIVE LOGITS
     Machina
    0.74
    arthed
    0.71
    ãĥ¼ãĥ³
    0.70
     Tradable
    0.69
    ittee
    0.67
     ILCS
    0.67
    atile
    0.67
    orable
    0.67
    eon
    0.66
    sembly
    0.66
    Activations Density 0.054%

    No Known Activations