© 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. 3642
    Prev
    Next
    INDEX
    Explanations

    names of political figures

    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
    481
    +0.19
    0.9%
    447
    +0.12
    0.5%
    430
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.19
    0.04
    46
    +0.12
    0.04
    443
    +0.10
    0.03
    Negative Logits
    Native
    -0.76
     Kear
    -0.73
     Siber
    -0.70
    Load
    -0.68
    Lex
    -0.66
     Ryder
    -0.66
    Roberts
    -0.66
    ages
    -0.66
     Polaris
    -0.65
     Parenthood
    -0.64
    POSITIVE LOGITS
     Jinping
    1.07
     appoint
    1.05
     administration
    0.99
     supporters
    0.97
     appointed
    0.97
     campaigned
    0.89
    jriwal
    0.83
     congratulated
    0.83
     supporter
    0.82
     presided
    0.82
    Activations Density 0.089%

    No Known Activations