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. 174
    Prev
    Next
    INDEX
    Explanations

    mentions related to renewable energy and sustainable economy initiatives

    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
    +0.26
    1.1%
    1385
    +0.12
    0.5%
    1842
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.26
    0.07
    1120
    +0.12
    0.03
    1499
    +0.09
    0.06
    Negative Logits
    <bos>
    -2.76
    ⓧ
    -0.98
    <?
    -0.88
    
    
    -0.81
    /**
    -0.80
    /*
    -0.70
    /***
    
    -0.66
    💼
    -0.65
    #
    -0.58
    //---
    -0.58
    POSITIVE LOGITS
     ecru
    1.60
     swarovski
    1.50
     hcm
    1.42
     Juf
    1.39
     bandung
    1.35
     eiffel
    1.34
     bordeaux
    1.33
     tupperware
    1.30
     hairc
    1.30
     murano
    1.29
    Activations Density 0.562%

    No Known Activations