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. 19124
    Prev
    Next
    INDEX
    Explanations

    information related to financial aspects, including salaries and economic data

    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
    194
    +0.10
    0.5%
    469
    +0.10
    0.5%
    405
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.10
    0.03
    278
    +0.10
    0.03
    686
    +0.09
    0.03
    Negative Logits
    alter
    -0.77
    actionDate
    -0.76
    kay
    -0.75
    faith
    -0.74
    redo
    -0.73
    ãĤ¦ãĤ¹
    -0.71
    ¬¼
    -0.71
    pecially
    -0.70
    unity
    -0.69
    prototype
    -0.69
    POSITIVE LOGITS
     earners
    0.82
     category
    0.79
     sectors
    0.78
     segment
    0.78
     item
    0.78
     ever
    0.77
     commodity
    0.77
     globally
    0.75
     overall
    0.75
     chunk
    0.75
    Activations Density 0.093%

    No Known Activations