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. 9170
    Prev
    Next
    INDEX
    Explanations

    technical terms related to field service management software and solutions

    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
    +0.33
    1.5%
    876
    +0.13
    0.6%
    1403
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.33
    -0.06
    1403
    +0.13
    0.07
    678
    +0.11
    0.13
    Negative Logits
    <bos>
    -3.24
    /***
    
    -1.03
    <?
    -0.97
    ⓧ
    -0.92
    
    
    -0.85
    ///**
    -0.79
    /**
    -0.78
    /*!
    
    -0.74
    lateinit
    -0.68
    /*
    -0.66
    POSITIVE LOGITS
     lele
    1.34
     bandung
    1.31
     milano
    1.17
     alpes
    1.13
     maroc
    1.12
     loto
    1.05
     valencia
    1.05
     bayern
    1.04
     ananas
    1.04
     teras
    1.04
    Activations Density 3.289%

    No Known Activations