Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 41180
    Prev
    Next
    INDEX
    Explanations

    names of places or geographical locations

    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
    224
    +0.12
    0.5%
    282
    +0.10
    0.4%
    304
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.12
    0.02
    659
    +0.10
    0.02
    556
    +0.09
    0.02
    Negative Logits
    arers
    -0.85
    apple
    -0.84
    glers
    -0.84
    ebook
    -0.77
    isite
    -0.76
    holding
    -0.75
    iners
    -0.75
    ocument
    -0.74
    lance
    -0.73
    onies
    -0.72
    POSITIVE LOGITS
     Kab
    0.92
    Benz
    0.77
     Kaz
    0.75
     Kats
    0.74
     Zen
    0.74
    henko
    0.74
    ovych
    0.74
     Dim
    0.73
     Dortmund
    0.73
     Kon
    0.73
    Activations Density 0.024%

    No Known Activations