Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8403
    Prev
    Next
    INDEX
    Explanations

    words related to nations or countries

    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
    288
    +0.10
    0.5%
    607
    +0.10
    0.4%
    97
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    97
    +0.10
    0.02
    312
    +0.10
    0.02
    752
    +0.10
    0.03
    Negative Logits
    imon
    -0.85
    ensions
    -0.70
     Packs
    -0.65
    Det
    -0.65
    Initialized
    -0.63
     Delivery
    -0.62
    ioned
    -0.62
    omething
    -0.62
     Dj
    -0.60
    NB
    -0.60
    POSITIVE LOGITS
    wide
    1.05
     premiere
    0.80
    liest
    0.79
     skyline
    0.77
    osphere
    0.77
    's
    0.76
    orest
    0.72
    isphere
    0.72
    istar
    0.72
    ilogy
    0.71
    Activations Density 0.061%

    No Known Activations