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. 439
    Prev
    Next
    INDEX
    Explanations

    business-related terms and activities, such as store openings, hiring, and company launches

    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
    529
    +0.09
    0.4%
    300
    +0.09
    0.4%
    688
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.09
    0.07
    761
    +0.09
    0.04
    59
    +0.09
    0.04
    Negative Logits
    Downloadha
    -0.76
    microsoft
    -0.66
     supposed
    -0.65
    Therefore
    -0.65
     Oops
    -0.64
     goddamn
    -0.63
     mattered
    -0.62
    ghazi
    -0.62
    Eva
    -0.62
     whiff
    -0.61
    POSITIVE LOGITS
     additional
    0.86
     unspecified
    0.82
     another
    0.80
     similar
    0.73
     someday
    0.71
     2019
    0.70
     tomorrow
    0.69
     future
    0.69
     sometime
    0.68
     proposals
    0.68
    Activations Density 0.273%

    No Known Activations