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. 697
    Prev
    Next
    INDEX
    Explanations

    information related to environmental pollution and health risks, particularly focusing on chemicals and pollutants

    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
    +0.24
    0.9%
    468
    +0.12
    0.5%
    1842
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.24
    0.08
    468
    +0.12
    0.06
    100
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.84
    ⓧ
    -0.83
    /**
    -0.76
    <?
    -0.68
    <!--
    
    -0.67
    /***
    
    -0.63
    //---
    -0.62
    <tfoot>
    -0.62
    <?
    
    -0.62
    //----
    -0.61
    POSITIVE LOGITS
     hcm
    1.13
     saar
    1.09
     magis
    1.06
     bandung
    1.03
     lele
    0.99
     levis
    0.98
     haup
    0.97
     glau
    0.97
     naer
    0.96
     aen
    0.94
    Activations Density 0.923%

    No Known Activations