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. 664
    Prev
    Next
    INDEX
    Explanations

    real estate property descriptions, specifically focusing on features like bathrooms and kitchen counters

    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
    +0.32
    1.4%
    1870
    +0.11
    0.5%
    1150
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.32
    0.20
    1870
    +0.11
    0.07
    1013
    +0.11
    0.16
    Negative Logits
    <bos>
    -2.28
    /***
    
    -0.92
    ⓧ
    -0.88
    
    
    -0.81
    ///**
    -0.80
    /**
    -0.74
    <?
    -0.73
    <?
    
    -0.71
    /*
    -0.67
    /*!
    
    -0.67
    POSITIVE LOGITS
     jawa
    1.08
     Minang
    1.07
     maroc
    1.00
     kebaya
    0.97
     bandung
    0.97
     jaya
    0.97
     jati
    0.97
     montagna
    0.94
     Nusantara
    0.93
     riva
    0.92
    Activations Density 3.007%

    No Known Activations