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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 12212
    Prev
    Next
    INDEX
    Explanations

    words related to Indigenous culture and identity

    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
    481
    +0.15
    0.7%
    86
    +0.10
    0.5%
    494
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.15
    0.03
    401
    +0.10
    0.03
    288
    +0.10
    0.03
    Negative Logits
    inventoryQuantity
    -0.84
    eus
    -0.84
    ascript
    -0.81
    ortex
    -0.75
    quickShipAvailable
    -0.74
    ifice
    -0.73
     ellipt
    -0.72
    etting
    -0.69
     horizont
    -0.68
    ullivan
    -0.68
    POSITIVE LOGITS
    istani
    1.02
     nationalists
    1.02
     nationalist
    0.98
     villagers
    0.96
     Nadu
    0.94
     separatist
    0.92
     separatists
    0.91
    istan
    0.88
     youths
    0.87
     labou
    0.87
    Activations Density 0.091%

    No Known Activations