© 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. 45558
    Prev
    Next
    INDEX
    Explanations

    references to the term "citizen."

    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
    302
    +0.13
    0.6%
    288
    +0.12
    0.6%
    465
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    302
    +0.13
    0.02
    567
    +0.12
    0.01
    465
    +0.10
    0.01
    Negative Logits
    hiba
    -0.86
    ension
    -0.76
    hift
    -0.74
    creen
    -0.73
    ammers
    -0.71
    ensions
    -0.71
    mith
    -0.71
    heet
    -0.71
    ended
    -0.69
    mers
    -0.69
    POSITIVE LOGITS
    ry
    1.17
     Citizen
    0.85
    hood
    0.84
     citizen
    0.80
    ially
    0.78
    fare
    0.71
     Kane
    0.71
    aer
    0.68
     uprising
    0.68
    ial
    0.65
    Activations Density 0.008%

    No Known Activations