© 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 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. 9020
    Prev
    Next
    INDEX
    Explanations

    names of political figures or organizations

    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
    497
    +0.12
    0.6%
    444
    +0.12
    0.5%
    302
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.12
    0.01
    232
    +0.12
    0.01
    302
    +0.11
    0.01
    Negative Logits
    Ùĩ
    -0.68
     caution
    -0.67
    MORE
    -0.62
    oise
    -0.62
     Rica
    -0.59
     Hels
    -0.59
    hold
    -0.59
     Haz
    -0.59
     Albion
    -0.58
     Saud
    -0.57
    POSITIVE LOGITS
    ptoms
    1.31
    pson
    1.30
    posium
    1.16
    otor
    1.03
    aceutical
    0.96
    otion
    0.93
    ichael
    0.91
    otos
    0.90
    achine
    0.90
    iasm
    0.89
    Activations Density 0.017%

    No Known Activations