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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 37302
    Prev
    Next
    INDEX
    Explanations

    references to individuals named "San."

    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
    195
    +0.14
    0.7%
    19
    +0.11
    0.5%
    421
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.14
    0.01
    232
    +0.11
    0.02
    421
    +0.11
    0.02
    Negative Logits
    llor
    -0.71
    llers
    -0.70
    ï¸ı
    -0.69
     clipboard
    -0.66
     Clarkson
    -0.65
     cider
    -0.65
    wig
    -0.64
     DUI
    -0.63
     Marketplace
    -0.62
     depreciation
    -0.61
    POSITIVE LOGITS
    ctuary
    1.10
    gha
    1.09
    itary
    1.05
    San
    1.01
    ctions
    1.01
    ction
    1.00
     Diego
    0.96
    afi
    0.95
     Francisco
    0.95
    itiz
    0.92
    Activations Density 0.012%

    No Known Activations