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 49152
    5. 8-RES_FS49152-JB
    6. 12100
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to the concept of "all."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    314
    +0.11
    0.5%
    460
    +0.09
    0.4%
    242
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    242
    +0.11
    0.01
    424
    +0.09
    0.01
    460
    +0.09
    0.01
    Negative Logits
    quickShipAvailable
    -0.74
    inho
    -0.71
    MX
    -0.69
     Loft
    -0.63
    namese
    -0.62
    Cub
    -0.60
    cel
    -0.60
    LR
    -0.58
    RL
    -0.58
    FR
    -0.57
    POSITIVE LOGITS
    igators
    0.90
     else
    0.87
    iances
    0.86
    igator
    0.85
    ocating
    0.83
    ogene
    0.76
    uding
    0.70
    tests
    0.70
    ying
    0.68
     sorts
    0.67
    Activations Density 0.007%

    No Known Activations