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. 26420
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "by" indicating attribution or authorship

    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
    584
    +0.12
    0.5%
    362
    +0.12
    0.5%
    420
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    584
    +0.12
    0.02
    362
    +0.12
    0.02
    658
    +0.10
    0.02
    Negative Logits
    isms
    -0.81
    hops
    -0.77
    idences
    -0.77
    worthiness
    -0.73
    database
    -0.73
    zone
    -0.72
    leeve
    -0.72
    uality
    -0.70
    bra
    -0.70
    olate
    -0.69
    POSITIVE LOGITS
     Ay
    0.92
     Todd
    0.91
     Christine
    0.88
     Stephen
    0.87
     Ellen
    0.86
     Richard
    0.85
     Tom
    0.85
     Yosh
    0.83
     former
    0.83
     Shinzo
    0.83
    Activations Density 0.032%

    No Known Activations