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. 23953
    Prev
    Next
    INDEX
    Explanations

    terms related to geek and nerd culture

    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
    +0.11
    0.5%
    568
    +0.11
    0.5%
    302
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    568
    +0.11
    0.01
    326
    +0.11
    0.01
    701
    +0.11
    0.01
    Negative Logits
    undai
    -0.79
     Liberties
    -0.67
    ugal
    -0.65
     redistributed
    -0.64
     Parenthood
    -0.62
    utions
    -0.62
     unbeaten
    -0.61
     miscar
    -0.61
    itars
    -0.61
    apeake
    -0.61
    POSITIVE LOGITS
     geek
    1.08
     nerd
    0.99
    iness
    0.95
    core
    0.93
    hack
    0.90
    Crunch
    0.88
     nerds
    0.88
    iest
    0.87
    hattan
    0.86
    y
    0.86
    Activations Density 0.020%

    No Known Activations