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. 6-RES-JB
    6. 780
    Prev
    Next
    INDEX
    Explanations

    key features and selling points of a product or service, possibly related to pets or home decor

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.25
    1.7%
    478
    +0.12
    0.8%
    1937
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.25
    0.08
    131
    +0.12
    0.07
    144
    +0.11
    0.07
    Negative Logits
    <bos>
    -2.93
    /**
    -1.18
    ⓧ
    -0.92
    /*
    -0.86
    
    
    -0.82
    <?
    
    -0.79
    <?
    -0.77
    /***
    
    -0.73
    ///**
    -0.69
    <!--
    
    -0.67
    POSITIVE LOGITS
     véhic
    0.92
     Our
    0.89
    Our
    0.88
     Juf
    0.87
     Khart
    0.86
     Pekan
    0.86
     Punj
    0.86
     Keny
    0.84
     réput
    0.84
     our
    0.82
    Activations Density 0.205%

    No Known Activations