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 3072
    5. 8-RES_FS3072-JB
    6. 652
    Prev
    Next
    INDEX
    Explanations

    references to financial and economic concepts related to borrowing, taxes, banking, and debt

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    718
    +0.12
    0.5%
    288
    +0.10
    0.5%
    97
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.08
    97
    +0.10
    0.05
    737
    +0.10
    0.06
    Negative Logits
    inventoryQuantity
    -0.86
    urations
    -0.77
    sbm
    -0.74
    POS
    -0.69
    Database
    -0.68
    Berry
    -0.68
    ocry
    -0.67
    Accessory
    -0.65
    Visual
    -0.65
     cue
    -0.64
    POSITIVE LOGITS
    wide
    1.52
    men
    1.02
    oslov
    0.93
    liness
    0.89
    ESE
    0.86
    hood
    0.83
     Laos
    0.81
    side
    0.81
     invaded
    0.74
     bordering
    0.74
    Activations Density 0.611%

    No Known Activations