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. 23048
    Prev
    Next
    INDEX
    Explanations

    references to Australian and UK websites or content

    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
    186
    +0.10
    0.4%
    219
    +0.09
    0.4%
    515
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.10
    0.02
    221
    +0.09
    0.01
    477
    +0.09
    0.01
    Negative Logits
     filibuster
    -0.69
    Grade
    -0.67
    Ö¼
    -0.67
    busters
    -0.65
    ocratic
    -0.65
    ogenic
    -0.65
    manship
    -0.63
    milo
    -0.63
    pring
    -0.62
     Nichols
    -0.62
    POSITIVE LOGITS
    /?
    0.96
     Lumpur
    0.77
    gypt
    0.77
    ploy
    0.68
    /#
    0.68
    /,
    0.68
     âĢº
    0.67
    ttp
    0.67
    ecd
    0.66
    gallery
    0.66
    Activations Density 0.022%

    No Known Activations