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. 813
    Prev
    Next
    INDEX
    Explanations

    instances of the word "but" and its context in contrasting statements

    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
    1.4%
    1068
    +0.11
    0.5%
    528
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1276
    +0.33
    0.11
    1068
    +0.11
    0.10
    555
    +0.10
    0.09
    Negative Logits
    <bos>
    -2.82
    /***
    
    -0.88
    ⓧ
    -0.80
    <?
    
    -0.66
    expandindo
    -0.66
    //*/
    -0.63
     /**
    
    -0.62
    /*++
    -0.61
     diagon
    -0.60
    };*/
    -0.56
    POSITIVE LOGITS
     hornblende
    0.78
     particolar
    0.78
     soulign
    0.77
    nhung
    0.74
     Minang
    0.73
     signora
    0.72
     But
    0.70
     ngunit
    0.70
     véhic
    0.69
     Putih
    0.69
    Activations Density 0.285%

    No Known Activations