© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 41518
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Nadine" or its variations in contexts related to personal experiences and food choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    612
    +0.12
    0.5%
    195
    +0.12
    0.5%
    187
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    612
    +0.12
    0.01
    628
    +0.12
    0.01
    539
    +0.11
    0.01
    Negative Logits
    oldown
    -0.75
    chnology
    -0.71
    fare
    -0.69
     contraception
    -0.67
    #$
    -0.67
    è¦ļéĨĴ
    -0.66
     simmer
    -0.66
     steril
    -0.65
     è£ı
    -0.65
     unsupported
    -0.63
    POSITIVE LOGITS
     Nad
    0.97
    ifiers
    0.94
    ras
    0.91
    uran
    0.90
    inished
    0.88
    atal
    0.88
    aya
    0.87
    ler
    0.87
    azi
    0.87
    rist
    0.86
    Activations Density 0.002%

    No Known Activations