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. 689
    Prev
    Next
    INDEX
    Explanations

    the word "anything" in various contexts

    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
    +0.25
    1.3%
    1984
    +0.12
    0.6%
    1296
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    971
    +0.25
    0.04
    1335
    +0.12
    0.04
    1811
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.67
    ⓧ
    -0.87
    /*
    -0.81
    
    
    -0.75
    /***
    
    -0.71
    #![
    -0.66
    /**
    -0.66
    <?
    -0.64
    Таким
    -0.57
    $_['
    -0.56
    POSITIVE LOGITS
     riva
    1.31
     lele
    1.30
     maroc
    1.30
     Czechos
    1.25
     tramont
    1.25
     riviera
    1.19
     bandung
    1.19
     ANYTHING
    1.18
     kokos
    1.14
     silikon
    1.11
    Activations Density 0.038%

    No Known Activations