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. 1031
    Prev
    Next
    INDEX
    Explanations

    dates in the format "Month Day, Year" in a text

    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
    250
    +0.11
    0.5%
    527
    +0.10
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.01
    247
    +0.10
    0.01
    194
    +0.10
    0.01
    Negative Logits
    phalt
    -0.75
    ospace
    -0.73
     crochet
    -0.73
    swer
    -0.73
     amen
    -0.72
    =""
    -0.72
    XL
    -0.71
    usercontent
    -0.71
    âĹ¼
    -0.71
     newsletters
    -0.71
    POSITIVE LOGITS
     Bai
    0.75
     Cursed
    0.68
     duel
    0.67
     Berserker
    0.66
     Kuro
    0.65
     punishing
    0.65
     Norris
    0.64
     Thief
    0.62
     Mages
    0.61
     summoned
    0.60
    Activations Density 0.037%

    No Known Activations