© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14915
    Prev
    Next
    INDEX
    Explanations

    organizations or movements related to gun control advocacy and activism

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    754
    +0.10
    0.4%
    496
    +0.10
    0.4%
    730
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.10
    0.04
    359
    +0.10
    0.04
    398
    +0.10
    0.04
    Negative Logits
     disg
    -0.85
    gue
    -0.81
     arsen
    -0.80
     circumst
    -0.79
     lapse
    -0.74
     simulator
    -0.74
     weakness
    -0.72
     brute
    -0.71
    htaking
    -0.70
     mechanically
    -0.69
    POSITIVE LOGITS
     Coalition
    1.28
     Initiative
    1.27
     Fund
    1.13
     Solutions
    1.12
     Foundation
    1.11
     Movement
    1.09
     Caucus
    1.07
     Campaign
    1.05
     Voters
    1.04
     Organizations
    1.02
    Activations Density 0.227%

    No Known Activations