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. 1074
    Prev
    Next
    INDEX
    Explanations

    instances of commentary or reporting related to controversial subjects

    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
    +0.24
    1.1%
    1150
    +0.16
    0.7%
    382
    +0.16
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.24
    0.09
    1535
    +0.16
    0.07
    2034
    +0.16
    0.07
    Negative Logits
    <bos>
    -2.15
    ⓧ
    -1.26
    <?
    -1.04
    
    
    -1.01
    /**
    -1.01
    <?
    
    -0.95
    /***
    
    -0.94
     thermomix
    -0.90
    //*/
    -0.88
     nutella
    -0.88
    POSITIVE LOGITS
     néanmoins
    0.78
     soigneusement
    0.72
     véhic
    0.72
     habituellement
    0.71
     soulign
    0.70
     spécialement
    0.68
     épu
    0.68
     exclusivement
    0.68
     fréquemment
    0.65
    graphicx
    0.65
    Activations Density 0.347%

    No Known Activations