© 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. 16708
    Prev
    Next
    INDEX
    Explanations

    actions or events related to legal or political 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
    87
    +0.35
    1.9%
    373
    +0.17
    0.9%
    500
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.35
    -0.02
    59
    +0.17
    0.05
    766
    +0.09
    0.05
    Negative Logits
    aces
    -0.72
    ibles
    -0.67
    cedented
    -0.67
    united
    -0.65
    eworld
    -0.62
    LGBT
    -0.62
    usalem
    -0.61
    ampions
    -0.61
    olitics
    -0.58
    amous
    -0.58
    POSITIVE LOGITS
     Vaugh
    0.68
     Ambro
    0.65
     Byrne
    0.63
     Constantin
    0.61
     Irwin
    0.59
     someone
    0.58
     respondent
    0.58
     Atkinson
    0.58
     Cyr
    0.57
     "_
    0.57
    Activations Density 0.928%

    No Known Activations