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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 8332
    Prev
    Next
    INDEX
    Explanations

    technology-related terms and product details, including mentions of specific tech companies like Amazon, AMD, Ford, Microsoft, and Google

    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
    447
    +0.30
    1.4%
    481
    +0.17
    0.8%
    461
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.30
    0.05
    346
    +0.17
    0.06
    736
    +0.09
    0.04
    Negative Logits
     thereof
    -0.67
    ο
    -0.67
    Ïī
    -0.66
    Õ
    -0.65
     ..."
    -0.65
     thereto
    -0.62
     guiActiveUnfocused
    -0.59
    Magikarp
    -0.58
    20439
    -0.57
     UTC
    -0.55
    POSITIVE LOGITS
    theless
    0.83
     reacts
    0.81
    sonian
    0.77
    odore
    0.76
     responds
    0.73
     Comes
    0.72
     also
    0.71
     responded
    0.71
     meanwhile
    0.71
     spokesman
    0.70
    Activations Density 0.213%

    No Known Activations