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. 23766
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Olivia" in various contexts

    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
    339
    +0.14
    0.7%
    71
    +0.13
    0.6%
    267
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.02
    288
    +0.13
    0.03
    232
    +0.11
    0.02
    Negative Logits
    ifying
    -0.93
    istically
    -0.85
    ificent
    -0.85
    ific
    -0.80
    icals
    -0.80
    icum
    -0.80
    ifiers
    -0.80
    anguage
    -0.78
    arians
    -0.78
    ifies
    -0.78
    POSITIVE LOGITS
    lihood
    0.85
    terness
    0.72
     Wilde
    0.72
    nc
    0.71
    ttes
    0.70
     Pigs
    0.69
    nen
    0.67
    rial
    0.67
    ķ
    0.67
    TION
    0.66
    Activations Density 0.068%

    No Known Activations