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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 37056
    Prev
    Next
    INDEX
    Explanations

    statements of ambition or objectives

    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
    247
    +0.15
    0.7%
    128
    +0.10
    0.4%
    16
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.15
    0.03
    355
    +0.10
    0.02
    16
    +0.09
    0.02
    Negative Logits
    oute
    -0.77
    ols
    -0.73
    CV
    -0.67
    dor
    -0.65
    loo
    -0.64
    greg
    -0.63
    nces
    -0.63
     Solitaire
    -0.63
    iannopoulos
    -0.62
    OUP
    -0.61
    POSITIVE LOGITS
    posts
    1.14
     Goal
    0.93
    goal
    0.90
    lessly
    0.86
    Goal
    0.85
    post
    0.84
     scorer
    0.82
     goal
    0.82
     accomplished
    0.77
    setting
    0.75
    Activations Density 0.021%

    No Known Activations