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. 987
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Patrick"

    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
    +0.14
    0.8%
    251
    +0.12
    0.7%
    1921
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.14
    0.02
    251
    +0.12
    0.02
    1921
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.15
    
    
    -0.72
    /*
    -0.70
    awtextra
    -0.69
    ⓧ
    -0.67
    مصادر
    -0.66
    <?
    
    -0.65
    PerformLayout
    -0.62
    webElementXpaths
    -0.61
    ByVersion
    -0.60
    POSITIVE LOGITS
     Patrick
    1.48
     patrick
    1.45
    Patrick
    1.41
     kram
    1.21
     PATRICK
    1.14
     Hæ
    1.06
    PATRICK
    1.06
     kac
    1.04
     karton
    1.02
     Kategor
    1.00
    Activations Density 0.038%

    No Known Activations