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. 23822
    Prev
    Next
    INDEX
    Explanations

    references to payload specifications and related elements within discussions of technology or aerospace contexts

    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
    288
    +0.13
    0.6%
    649
    +0.11
    0.5%
    350
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.13
    0.01
    34
    +0.11
    0.01
    40
    +0.10
    0.01
    Negative Logits
    âĸ¬âĸ¬
    -0.77
    lex
    -0.70
    Ire
    -0.69
     Roses
    -0.69
    rupt
    -0.67
    pmwiki
    -0.67
    baum
    -0.66
    gov
    -0.66
     Rhythm
    -0.66
    ected
    -0.66
    POSITIVE LOGITS
     payload
    1.15
    s
    0.92
     bay
    0.85
     tray
    0.78
    romeda
    0.76
    sburg
    0.75
     capacity
    0.75
     shipment
    0.74
    sheet
    0.74
     baskets
    0.73
    Activations Density 0.003%

    No Known Activations