© 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. 45827
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals, particularly those with the surname 'Lawson' or 'Nicholson'

    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
    447
    +0.20
    0.9%
    659
    +0.13
    0.6%
    326
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.20
    0.01
    502
    +0.13
    0.01
    672
    +0.10
    0.01
    Negative Logits
    estones
    -0.87
    izoph
    -0.86
    estone
    -0.83
    astical
    -0.77
    natureconservancy
    -0.74
    ths
    -0.73
    stood
    -0.68
    thro
    -0.68
    board
    -0.67
    liest
    -0.67
    POSITIVE LOGITS
     Lawson
    1.01
     Norton
    0.74
    Counter
    0.65
     Brewer
    0.64
    sey
    0.63
     Miller
    0.62
     Jarrett
    0.60
     Jarvis
    0.58
    ery
    0.58
     Alley
    0.57
    Activations Density 0.005%

    No Known Activations