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. 6733
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "was."

    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
    +0.37
    2.1%
    1023
    +0.16
    0.9%
    1909
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1023
    +0.37
    0.09
    658
    +0.16
    0.08
    1909
    +0.11
    0.07
    Negative Logits
    <bos>
    -3.00
    ///**
    -0.77
    public
    -0.64
    if
    -0.59
    //
    -0.59
    quot
    -0.59
    /**
    -0.56
     which
    -0.56
    /**
    
    -0.56
    struct
    -0.55
    POSITIVE LOGITS
     accla
    1.39
     thut
    1.38
     fatis
    1.38
     reft
    1.37
     guarante
    1.35
     effe
    1.35
     increa
    1.34
     ftu
    1.34
     perfon
    1.32
     Minang
    1.32
    Activations Density 0.277%

    No Known Activations