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. 10-RES-JB
    6. 6841
    Prev
    Next
    INDEX
    Explanations

    references to offices and teams involved in political campaigns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.23
    0.8%
    227
    +0.12
    0.4%
    1870
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.23
    0.05
    2025
    +0.12
    0.04
    299
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.77
    ByVersion
    -0.58
     /**
    
    -0.53
    ///**
    -0.52
    public
    -0.50
    /**
    -0.49
    /*
    -0.49
    SPECTION
    -0.49
    Жа
    -0.49
    InvalidProtocol
    -0.48
    POSITIVE LOGITS
     resear
    1.11
     suspic
    1.10
     accla
    1.10
     emphat
    1.10
     disagre
    1.09
     thut
    1.06
     shenan
    1.04
     unwarran
    1.03
     Minang
    1.02
     obstin
    1.00
    Activations Density 0.259%

    No Known Activations