Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1099
    Prev
    Next
    INDEX
    Explanations

    references to legal or official documents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    659
    +0.19
    0.9%
    67
    +0.13
    0.6%
    578
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.19
    0.12
    67
    +0.13
    0.09
    578
    +0.12
    0.06
    Negative Logits
    uyomi
    -0.68
     Tinder
    -0.68
     Yamaha
    -0.68
     GOODMAN
    -0.66
     Chero
    -0.65
     track
    -0.62
     timeout
    -0.62
    ãĥĹ
    -0.61
     Gors
    -0.58
     Bain
    -0.58
    POSITIVE LOGITS
    overed
    1.30
    rossover
    1.26
    ologne
    1.23
    ursor
    1.23
    auldron
    1.22
    rouch
    1.22
    URRENT
    1.21
    oding
    1.19
    ategor
    1.18
    actus
    1.18
    Activations Density 0.273%

    No Known Activations