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. 589
    Prev
    Next
    INDEX
    Explanations

    information related to environmental changes and their impacts, such as rising sea levels, climate change, and weather conditions

    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
    +0.27
    1.5%
    1510
    +0.11
    0.6%
    1896
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1510
    +0.27
    0.06
    1637
    +0.11
    0.06
    521
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.77
    ⓧ
    -0.92
    /***
    
    -0.86
    
    
    -0.80
    <?
    
    -0.78
     /**
    
    -0.74
     intersper
    -0.69
     disbur
    -0.68
    <?
    -0.67
    ///**
    -0.67
    POSITIVE LOGITS
     seksi
    0.75
     kafe
    0.72
     Minang
    0.71
     soulign
    0.69
     véhic
    0.69
     Muhamma
    0.69
     catég
    0.69
    >\<
    0.66
     makam
    0.64
     Hitam
    0.64
    Activations Density 0.326%

    No Known Activations