© 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. 2388
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws and government policies, particularly regarding state and local levels

    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
    31
    +0.13
    0.6%
    611
    +0.10
    0.5%
    409
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.13
    0.04
    152
    +0.10
    0.04
    508
    +0.10
    0.03
    Negative Logits
    veyard
    -0.85
    xual
    -0.81
    cellent
    -0.80
    ocious
    -0.77
    opsis
    -0.74
    ffiti
    -0.72
    enment
    -0.71
     Guilty
    -0.70
    qq
    -0.69
    selage
    -0.69
    POSITIVE LOGITS
     governments
    1.38
     legislatures
    1.29
     jurisdictions
    1.29
     agencies
    1.11
     departments
    1.11
     Governments
    1.06
     districts
    1.04
     populations
    1.03
     municipalities
    1.03
     mayors
    1.03
    Activations Density 0.088%

    No Known Activations