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. 12056
    Prev
    Next
    INDEX
    Explanations

    terms related to network protocols

    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
    640
    +0.14
    0.6%
    160
    +0.14
    0.6%
    346
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.14
    0.03
    107
    +0.14
    0.02
    158
    +0.10
    0.02
    Negative Logits
    ÙIJ
    -0.76
     JPM
    -0.75
     Sly
    -0.71
     Opportun
    -0.69
     à¨
    -0.68
     Dish
    -0.67
     MIT
    -0.66
     Reloaded
    -0.66
     Isabel
    -0.64
     Rodrig
    -0.64
    POSITIVE LOGITS
    EStreamFrame
    0.99
    train
    0.90
    dump
    0.89
    series
    0.88
    nom
    0.87
    government
    0.86
    main
    0.86
    tr
    0.85
    default
    0.85
    product
    0.85
    Activations Density 0.014%

    No Known Activations