© 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 24576
    9. 8-RES_FS24576-JB
    11. 19643
    Prev
    Next
    INDEX
    Explanations

    the name "Ian"

    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
    464
    +0.10
    0.5%
    527
    +0.10
    0.4%
    201
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.10
    0.01
    232
    +0.10
    0.01
    659
    +0.09
    0.01
    Negative Logits
    ktop
    -0.82
    perm
    -0.75
    DAQ
    -0.75
    stic
    -0.74
    âĶģ
    -0.71
    hips
    -0.71
    glers
    -0.67
    adobe
    -0.66
    stice
    -0.65
    stakes
    -0.64
    POSITIVE LOGITS
     Cheong
    1.09
     Fleming
    0.90
     Ian
    0.83
     Kers
    0.81
     McK
    0.80
     Desmond
    0.78
     Malcolm
    0.77
     MacDonald
    0.75
     Dice
    0.74
     Curtis
    0.74
    Activations Density 0.013%

    No Known Activations