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. 12057
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to space and space exploration organizations

    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
    44
    +0.12
    0.5%
    665
    +0.10
    0.5%
    386
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    730
    +0.12
    0.02
    287
    +0.10
    0.02
    386
    +0.10
    0.02
    Negative Logits
    ONES
    -0.78
    soDeliveryDate
    -0.75
    luaj
    -0.71
    xual
    -0.70
    20439
    -0.69
     Adidas
    -0.69
    UCT
    -0.68
    apon
    -0.66
    nai
    -0.66
    URR
    -0.66
    POSITIVE LOGITS
     Center
    0.98
     Observatory
    0.88
     Laboratory
    0.85
     Station
    0.73
     Laboratories
    0.69
     Centre
    0.69
     Library
    0.68
     laboratory
    0.67
     Institute
    0.65
     Science
    0.64
    Activations Density 0.039%

    No Known Activations