© 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. 20765
    Prev
    Next
    INDEX
    Explanations

    phrases related to negation or exceptions

    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
    437
    +0.11
    0.5%
    373
    +0.11
    0.5%
    638
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.11
    0.04
    61
    +0.11
    0.04
    643
    +0.09
    0.03
    Negative Logits
    stakes
    -0.81
    eers
    -0.74
     Frenzy
    -0.69
     Quarterly
    -0.64
     Circuit
    -0.64
    Techn
    -0.60
     Lessons
    -0.60
    pict
    -0.60
     tabl
    -0.59
     Term
    -0.59
    POSITIVE LOGITS
    epad
    1.33
    icably
    1.27
    hin
    1.18
     necessarily
    1.07
    ifying
    1.01
    icable
    1.01
     adequately
    0.94
    ched
    0.91
     liking
    0.91
    ifies
    0.88
    Activations Density 0.103%

    No Known Activations