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 · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 6797
    Prev
    Next
    INDEX
    Explanations

    pronouns related to individuals, particularly "he" and "she."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.39
    1.8%
    381
    +0.10
    0.5%
    687
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.39
    0.09
    1415
    +0.10
    0.05
    966
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.85
    <?
    -0.72
    
    
    -0.70
    /**
    -0.66
    SourceChecksum
    -0.62
    /*!
    
    -0.60
    PerformLayout
    -0.60
    #![
    -0.57
    <?
    
    -0.56
    expandindo
    -0.55
    POSITIVE LOGITS
     Jambi
    1.08
     Palembang
    1.04
     Minang
    0.97
     Czechos
    0.94
     maneu
    0.93
     unlaw
    0.91
     Makassar
    0.89
     accla
    0.86
    !!</
    0.86
     Muhamma
    0.86
    Activations Density 0.200%

    No Known Activations