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. 11464
    Prev
    Next
    INDEX
    Explanations

    details related to specific organizations or institutions, particularly those promoting education and activism

    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
    288
    +0.12
    0.6%
    766
    +0.10
    0.5%
    455
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.12
    0.04
    48
    +0.10
    0.03
    409
    +0.10
    0.03
    Negative Logits
    nos
    -0.69
    eger
    -0.67
     Koh
    -0.64
    hig
    -0.64
     Kinnikuman
    -0.63
     Strauss
    -0.63
    ozyg
    -0.62
    ĸļ
    -0.62
    kr
    -0.61
    yi
    -0.61
    POSITIVE LOGITS
     affairs
    0.62
     species
    0.59
     succession
    0.58
     armies
    0.57
     menace
    0.57
     regimes
    0.57
     army
    0.56
     Confederacy
    0.55
     population
    0.55
     oppress
    0.55
    Activations Density 0.099%

    No Known Activations