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. 23135
    Prev
    Next
    INDEX
    Explanations

    phrases or concepts related to ownership or possession

    oai_token-act-pair · gpt-4o-miniTriggered 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
    127
    +0.10
    0.5%
    339
    +0.10
    0.5%
    723
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.07
    608
    +0.10
    0.06
    385
    +0.10
    0.06
    Negative Logits
    sson
    -0.85
    stad
    -0.83
    Gallery
    -0.73
    req
    -0.73
    tsy
    -0.72
    ":[
    -0.71
    eting
    -0.71
    ozy
    -0.71
    lund
    -0.70
    ohan
    -0.68
    POSITIVE LOGITS
     own
    1.58
     predecessor
    1.19
    ELF
    1.14
     namesake
    1.04
     predecessors
    0.97
     Own
    0.95
     newest
    0.90
     tentacles
    0.89
     respective
    0.87
     flagship
    0.87
    Activations Density 0.143%

    No Known Activations