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. 21796
    Prev
    Next
    INDEX
    Explanations

    entities or concepts related to legislative changes or proposals

    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
    362
    +0.18
    0.9%
    393
    +0.15
    0.7%
    481
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.18
    0.09
    636
    +0.15
    0.05
    393
    +0.15
    0.06
    Negative Logits
    isson
    -0.86
    agree
    -0.77
    SPONSORED
    -0.77
    ccoli
    -0.75
    nil
    -0.73
    nesty
    -0.72
    full
    -0.72
    seekers
    -0.71
    allah
    -0.71
    llah
    -0.69
    POSITIVE LOGITS
     existing
    1.16
     entire
    0.99
     workforce
    0.90
     fundamentals
    0.88
     relationship
    0.86
     curriculum
    0.85
     wording
    0.84
     equation
    0.84
     landscape
    0.83
     offending
    0.82
    Activations Density 0.293%

    No Known Activations