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. 961
    Prev
    Next
    INDEX
    Explanations

    phrases related to involvement and responsibility in events or actions

    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
    +0.33
    1.3%
    1150
    +0.17
    0.7%
    453
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.33
    0.08
    1150
    +0.17
    0.04
    453
    +0.14
    0.07
    Negative Logits
    <bos>
    -2.82
    ⓧ
    -1.12
    /**
    -1.00
    <?
    -0.93
    
    
    -0.79
    #![
    -0.78
    /*
    -0.78
    /*++
    -0.75
    JAKARTA
    -0.72
    HasColumnType
    -0.72
    POSITIVE LOGITS
     maneu
    2.04
     Minang
    1.97
     reluct
    1.92
     accla
    1.83
     Keny
    1.81
     shenan
    1.80
     Juf
    1.75
     lele
    1.73
     viciss
    1.73
     inev
    1.72
    Activations Density 0.859%

    No Known Activations