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. 21672
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations or addresses

    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
    524
    +0.10
    0.5%
    593
    +0.10
    0.5%
    267
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.10
    0.04
    708
    +0.10
    0.03
    524
    +0.10
    0.03
    Negative Logits
     reproduce
    -0.69
     litres
    -0.67
     squads
    -0.66
    onom
    -0.66
    berman
    -0.65
     suits
    -0.64
    rogram
    -0.63
    orians
    -0.62
     adaptations
    -0.62
    arian
    -0.62
    POSITIVE LOGITS
     Rd
    1.04
     NW
    0.99
     Junction
    0.92
     intersection
    0.91
     Blvd
    0.87
     Northeast
    0.86
     Cemetery
    0.86
     Parkway
    0.86
     Boulevard
    0.86
    wy
    0.85
    Activations Density 0.045%

    No Known Activations