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. 608
    Prev
    Next
    INDEX
    Explanations

    names of famous authors

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    238
    +0.11
    0.5%
    554
    +0.11
    0.5%
    683
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.02
    288
    +0.11
    0.02
    232
    +0.11
    0.02
    Negative Logits
    ignment
    -0.76
    ition
    -0.72
    heed
    -0.69
    mith
    -0.69
    ulet
    -0.68
    rooms
    -0.65
    =-=-=-=-
    -0.64
    hur
    -0.64
    itol
    -0.63
    child
    -0.62
    POSITIVE LOGITS
     Hoover
    0.89
    ALLY
    0.87
    swick
    0.79
     Cheong
    0.78
     Draper
    0.77
     Ernest
    0.75
    ally
    0.73
     Hem
    0.72
     Byrne
    0.72
    ATIONS
    0.71
    Activations Density 0.047%

    No Known Activations