© 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. 5046
    Prev
    Next
    INDEX
    Explanations

    references to politics and government, including specific government agencies, political parties, and legislative actions

    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
    57
    +0.10
    0.5%
    715
    +0.10
    0.5%
    732
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.10
    0.06
    152
    +0.10
    0.06
    57
    +0.10
    0.05
    Negative Logits
    epad
    -0.84
    azaar
    -0.73
    ructure
    -0.71
    hid
    -0.69
    icter
    -0.67
    atron
    -0.66
    quad
    -0.65
    ebook
    -0.65
    otaur
    -0.65
    yy
    -0.64
    POSITIVE LOGITS
     taxpayers
    1.12
     citizens
    1.09
     soil
    0.99
     policymakers
    0.97
     citizenship
    0.93
     diplomats
    0.93
     Airlines
    0.93
     households
    0.93
     embassies
    0.93
     Citizenship
    0.91
    Activations Density 0.109%

    No Known Activations