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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5628
    Prev
    Next
    INDEX
    Explanations

    general statements about activities or plans

    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
    +0.17
    1.1%
    1705
    +0.14
    0.9%
    90
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.17
    0.07
    90
    +0.14
    0.05
    971
    +0.11
    0.05
    Negative Logits
    <bos>
    -3.32
    ⓧ
    -1.28
    <?
    -0.94
    
    
    -0.94
    /**
    -0.92
    /*
    -0.91
    /***
    
    -0.89
    #![
    -0.77
    Cringe
    -0.66
     endow
    -0.65
    POSITIVE LOGITS
     maroc
    1.12
     riva
    1.04
    Something
    1.03
     Something
    1.03
     SOMETHING
    1.02
     ananas
    1.02
    ">...
    1.01
     moza
    1.00
     something
    0.99
     lele
    0.99
    Activations Density 0.148%

    No Known Activations