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. 597
    Prev
    Next
    INDEX
    Explanations

    time-related events or actions

    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
    +0.19
    0.9%
    381
    +0.14
    0.7%
    1535
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1023
    +0.19
    0.08
    442
    +0.14
    0.08
    897
    +0.13
    0.08
    Negative Logits
    <bos>
    -2.62
    ⓧ
    -1.13
    <?
    -0.83
    /***
    
    -0.80
    /**
    -0.79
    /*
    -0.75
    
    
    -0.68
    ///**
    -0.64
     /**
    
    -0.61
    #![
    -0.59
    POSITIVE LOGITS
     soulign
    1.09
     catég
    1.02
     Juf
    1.01
     maksi
    1.00
     Keny
    0.99
     jaya
    0.98
     Febru
    0.95
     Balik
    0.95
    mavi
    0.95
     fortn
    0.95
    Activations Density 0.711%

    No Known Activations