© 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. 20577
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Not" in various contexts

    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
    241
    +0.11
    0.5%
    651
    +0.10
    0.5%
    638
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.11
    0.04
    226
    +0.10
    0.04
    61
    +0.10
    0.03
    Negative Logits
    velt
    -0.75
    stakes
    -0.66
    æĸ
    -0.64
    ç·
    -0.64
    artz
    -0.63
     contrasts
    -0.60
    åĤ
    -0.60
    hement
    -0.60
    ä¿
    -0.59
    assetsadobe
    -0.59
    POSITIVE LOGITS
    epad
    1.36
    eworthy
    1.23
    orious
    1.16
    ifications
    1.14
    ifier
    1.06
    icably
    1.04
    withstanding
    1.03
    ional
    1.01
    icable
    1.01
    ific
    0.98
    Activations Density 0.065%

    No Known Activations