© 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. 14881
    Prev
    Next
    INDEX
    Explanations

    phrases related to political policies and government actions at different levels of authority

    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
    120
    +0.11
    0.5%
    489
    +0.10
    0.5%
    759
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.06
    36
    +0.10
    0.06
    489
    +0.10
    0.04
    Negative Logits
     congratulations
    -0.73
     Congratulations
    -0.69
     Guinness
    -0.66
     Amen
    -0.64
     Chester
    -0.63
     Buzz
    -0.63
     Katherine
    -0.62
    upon
    -0.62
     Colo
    -0.61
     offerings
    -0.61
    POSITIVE LOGITS
     basis
    1.23
     periphery
    1.05
     level
    0.95
    ysical
    0.93
     standpoint
    0.92
     scale
    0.90
     interpersonal
    0.89
     societal
    0.86
     macro
    0.85
     broader
    0.84
    Activations Density 0.263%

    No Known Activations