© 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. 15396
    Prev
    Next
    INDEX
    Explanations

    responses in political discourse

    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
    447
    +0.20
    1.0%
    640
    +0.12
    0.6%
    679
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.20
    0.13
    679
    +0.12
    0.11
    640
    +0.12
    0.10
    Negative Logits
    quartered
    -0.83
    ounter
    -0.79
     fermented
    -0.77
     submerged
    -0.76
     inflated
    -0.75
     skewed
    -0.75
    eatured
    -0.74
     saturated
    -0.72
    thal
    -0.72
     baked
    -0.72
    POSITIVE LOGITS
     Otherwise
    1.24
     Especially
    1.11
     Because
    1.09
     Hopefully
    1.09
     Firstly
    1.05
     Ideally
    1.05
     Whether
    1.03
     Unless
    1.03
     If
    1.03
     Either
    1.03
    Activations Density 0.503%

    No Known Activations