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. 1122
    Prev
    Next
    INDEX
    Explanations

    references to the game and its elements

    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
    +0.30
    1.8%
    1909
    +0.13
    0.8%
    2011
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1909
    +0.30
    0.05
    783
    +0.13
    0.05
    406
    +0.12
    0.04
    Negative Logits
    <bos>
    -3.17
    /***
    
    -0.72
    /*
    -0.71
    /*++
    -0.68
     وتسجيلات
    -0.68
     springfox
    -0.66
    #![
    -0.66
    /**
    -0.65
     neutralize
    -0.65
    ///**
    -0.65
    POSITIVE LOGITS
     véhic
    1.14
     quoique
    1.05
     épu
    1.03
     quelcon
    1.00
     Minang
    0.98
     aveug
    0.98
     Intere
    0.98
     Simult
    0.96
     soulign
    0.96
     éprou
    0.94
    Activations Density 0.074%

    No Known Activations