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. 15060
    Prev
    Next
    INDEX
    Explanations

    calls to action in a customer service context

    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
    +0.23
    1.4%
    1124
    +0.10
    0.6%
    938
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    938
    +0.23
    0.06
    1763
    +0.10
    0.06
    214
    +0.09
    0.05
    Negative Logits
    <bos>
    -3.15
    ⓧ
    -1.10
    /**
    -0.84
    /*
    -0.82
    /***
    
    -0.80
    
    
    -0.79
    <?
    
    -0.76
    <?
    -0.75
    /*!
    
    -0.68
    #
    -0.62
    POSITIVE LOGITS
     affor
    1.43
     maneu
    1.42
     impra
    1.27
     reluct
    1.22
     increa
    1.21
     accla
    1.19
     disreg
    1.16
     stockholm
    1.16
     unden
    1.16
     unspeak
    1.16
    Activations Density 0.221%

    No Known Activations