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 24576
    5. 8-RES_FS24576-JB
    6. 23713
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "charter"

    oai_token-act-pair · gpt-4o-miniTriggered 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
    288
    +0.17
    0.8%
    302
    +0.12
    0.6%
    343
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.01
    343
    +0.12
    0.01
    302
    +0.12
    0.01
    Negative Logits
    Downloadha
    -0.80
    Lenin
    -0.73
    asio
    -0.69
    utenberg
    -0.67
     Lennon
    -0.67
    pez
    -0.63
     Rove
    -0.62
    ocate
    -0.62
     Imran
    -0.62
     Tot
    -0.60
    POSITIVE LOGITS
    icut
    0.91
    eer
    0.79
     charter
    0.76
    iffs
    0.72
    iff
    0.71
     Charter
    0.68
     entit
    0.67
    ray
    0.67
    plain
    0.66
    ions
    0.66
    Activations Density 0.014%

    No Known Activations