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 1536
    5. 8-RES_FS1536-JB
    6. 289
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental issues, agriculture, industry, and technology

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    694
    +0.11
    0.5%
    310
    +0.10
    0.4%
    647
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    647
    +0.11
    0.10
    694
    +0.10
    0.07
    121
    +0.10
    0.09
    Negative Logits
    idates
    -0.73
    lyak
    -0.69
    orate
    -0.69
    uliffe
    -0.68
    leeve
    -0.68
    erb
    -0.66
    istical
    -0.65
    oric
    -0.65
    olute
    -0.64
    ochond
    -0.63
    POSITIVE LOGITS
     ours
    0.93
    those
    0.85
    lihood
    0.77
     those
    0.77
     ones
    0.77
     yours
    0.76
     hers
    0.73
     weddings
    0.71
    unts
    0.68
     Hugo
    0.62
    Activations Density 1.886%

    No Known Activations