© 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. 5422
    Prev
    Next
    INDEX
    Explanations

    words related to societal issues or controversies

    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
    616
    +0.10
    0.5%
    251
    +0.10
    0.5%
    102
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    226
    +0.10
    0.03
    251
    +0.10
    0.03
    215
    +0.10
    0.03
    Negative Logits
     Madden
    -0.81
     briefs
    -0.74
     Grayson
    -0.73
     Pound
    -0.71
     Duo
    -0.69
     halves
    -0.69
     Tackle
    -0.67
     Blitz
    -0.67
     Ank
    -0.67
     Mayhem
    -0.66
    POSITIVE LOGITS
    fortunately
    1.37
    usual
    1.35
    iversity
    1.29
    stable
    1.28
    animous
    1.21
    ivers
    1.20
    necessary
    1.20
    expected
    1.20
    iverse
    1.19
    employment
    1.19
    Activations Density 0.015%

    No Known Activations