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. 996
    Prev
    Next
    INDEX
    Explanations

    words related to financial transactions and financial checks

    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
    314
    +0.14
    0.7%
    113
    +0.11
    0.5%
    659
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.14
    0.02
    129
    +0.11
    0.02
    119
    +0.11
    0.01
    Negative Logits
     Hots
    -0.85
    wcs
    -0.73
    BLE
    -0.66
     solitary
    -0.61
     Chrys
    -0.60
    ãĥĩ
    -0.60
    âĸ¬
    -0.58
     Argon
    -0.58
     Norn
    -0.58
    cipled
    -0.57
    POSITIVE LOGITS
    strap
    1.00
    boxes
    0.99
    book
    0.98
    box
    0.95
    enhagen
    0.94
    er
    0.92
    rolled
    0.91
    ups
    0.89
    books
    0.88
    lists
    0.88
    Activations Density 0.024%

    No Known Activations