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. 610
    Prev
    Next
    INDEX
    Explanations

    quotations from spokespeople

    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
    +0.21
    1.0%
    667
    +0.11
    0.5%
    1870
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.21
    0.03
    351
    +0.11
    0.02
    667
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.80
    
    
    -1.06
    ⓧ
    -1.05
    <?
    -0.96
    /**
    -0.91
    /*!
    
    -0.90
    /***
    
    -0.89
    <?
    
    -0.87
    ///**
    -0.79
    /*
    -0.78
    POSITIVE LOGITS
     bandung
    1.16
     Minang
    1.16
     spokespersons
    1.09
     unlaw
    1.08
     maneu
    1.07
     jaya
    1.06
     affor
    1.06
     territo
    1.06
     spokesman
    1.04
     sovere
    1.04
    Activations Density 0.077%

    No Known Activations