Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 69
    Prev
    Next
    INDEX
    Explanations

    postal addresses and related information such as phone numbers and bank details

    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
    +0.22
    0.8%
    1343
    +0.11
    0.4%
    1741
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1692
    +0.22
    0.02
    1343
    +0.11
    0.03
    139
    +0.08
    0.03
    Negative Logits
    <bos>
    -1.31
    ///**
    -0.93
    /***
    
    -0.92
    <?
    
    -0.83
    //};
    -0.79
    /*!
    
    -0.74
    //*/
    -0.70
    /**
    -0.70
    //});
    -0.64
    <>
    
    -0.62
    POSITIVE LOGITS
     bangkok
    0.91
     unden
    0.91
     stockholm
    0.89
     kyo
    0.88
     tokyo
    0.87
     blackpink
    0.86
     seoul
    0.86
     amsterdam
    0.84
     brooklyn
    0.84
     effe
    0.84
    Activations Density 0.054%

    No Known Activations