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. 513
    Prev
    Next
    INDEX
    Explanations

    names related to the Muslim community

    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
    +0.16
    0.8%
    759
    +0.14
    0.7%
    314
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.16
    0.02
    759
    +0.14
    0.02
    201
    +0.13
    0.02
    Negative Logits
     Rivals
    -0.77
     Collider
    -0.77
     Wolves
    -0.69
     CFR
    -0.69
     Tycoon
    -0.67
     Forge
    -0.65
    20439
    -0.64
     tits
    -0.64
     Stories
    -0.62
     park
    -0.61
    POSITIVE LOGITS
    rahim
    1.16
    afia
    0.99
     Rahman
    0.97
    renheit
    0.92
    allah
    0.90
    rah
    0.89
    aina
    0.89
    usal
    0.85
    jit
    0.84
    le
    0.84
    Activations Density 0.017%

    No Known Activations