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. 6817
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or circumstances that may change or be affected by external factors

    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
    +0.27
    1.0%
    856
    +0.09
    0.3%
    1373
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1148
    +0.27
    0.08
    1539
    +0.09
    0.05
    1592
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.47
     /**
    
    -0.58
    /***
    
    -0.57
     and
    -0.52
    //};
    -0.50
    вік
    -0.48
    //*/
    -0.47
     however
    -0.47
     or
    -0.46
    /*++
    -0.46
    POSITIVE LOGITS
    >\<
    0.73
     particolar
    0.72
     adatta
    0.69
     BoxFit
    0.68
     kokos
    0.67
     zove
    0.67
    :"-
    0.66
     présidenti
    0.64
    ℗
    0.62
     appréci
    0.61
    Activations Density 1.169%

    No Known Activations