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. 8427
    Prev
    Next
    INDEX
    Explanations

    Arabic characters and symbols

    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
    15
    +0.13
    0.6%
    376
    +0.10
    0.5%
    503
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    15
    +0.13
    0.01
    232
    +0.10
    0.01
    367
    +0.09
    0.01
    Negative Logits
     board
    -0.80
    uncture
    -0.77
    enegger
    -0.72
    hens
    -0.69
    ierrez
    -0.69
     CLSID
    -0.68
    BOOK
    -0.64
     PLoS
    -0.64
     Clicker
    -0.63
    PDATE
    -0.63
    POSITIVE LOGITS
    ¹
    1.29
    ¨
    1.26
    ª
    1.15
    £
    1.13
    ±
    1.07
    ¥
    1.07
    Į
    1.06
    «
    1.04
    ©
    1.04
    Ń
    1.00
    Activations Density 0.021%

    No Known Activations