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. 179
    Prev
    Next
    INDEX
    Explanations

    phrases related to comfort and discomfort

    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
    +0.18
    1.1%
    1047
    +0.12
    0.7%
    1805
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1047
    +0.18
    0.03
    1805
    +0.12
    0.03
    892
    +0.11
    0.03
    Negative Logits
    <bos>
    -3.00
    /**
    -0.96
    
    
    -0.92
    ⓧ
    -0.92
    /***
    
    -0.92
    <?
    -0.81
    <?
    
    -0.77
    ///**
    -0.74
    /*!
    
    -0.72
    #![
    -0.72
    POSITIVE LOGITS
     quoc
    1.07
    Comfort
    1.06
     Comfort
    1.06
     saar
    1.05
     COMFORT
    1.02
     kasa
    1.02
     bandung
    1.02
     maroc
    1.02
     jawa
    1.01
     kela
    0.99
    Activations Density 0.076%

    No Known Activations