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. 23344
    Prev
    Next
    INDEX
    Explanations

    statements made by individuals in a discussion or interview context

    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
    373
    +0.13
    0.6%
    756
    +0.11
    0.5%
    87
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    180
    +0.13
    0.06
    514
    +0.11
    0.04
    766
    +0.10
    0.04
    Negative Logits
    ãĥİ
    -0.72
    ãĥĥãĥĪ
    -0.67
    tumblr
    -0.66
    TABLE
    -0.65
    atible
    -0.62
    Contents
    -0.61
    Lens
    -0.61
    ranean
    -0.59
    ãĥīãĥ©ãĤ´ãĥ³
    -0.58
    Released
    -0.57
    POSITIVE LOGITS
     sarcast
    0.87
     adding
    0.78
     rhet
    0.73
    alsh
    0.73
     anecd
    0.73
     diplom
    0.73
     chuck
    0.70
     emphatically
    0.69
     bluntly
    0.67
     noting
    0.66
    Activations Density 0.122%

    No Known Activations