Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 7784
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "big" in various contexts

    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.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.34
    1.6%
    1757
    +0.13
    0.6%
    1350
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.34
    0.06
    405
    +0.13
    0.06
    1506
    +0.13
    0.05
    Negative Logits
    <bos>
    -1.62
    <?
    -0.69
    /*
    -0.63
    bigsqcup
    -0.63
    triangleq
    -0.62
    
    
    -0.61
    <tfoot>
    -0.57
     koc
    -0.57
    textnormal
    -0.57
    xymatrix
    -0.54
    POSITIVE LOGITS
     big
    1.20
     BIG
    1.13
    big
    1.08
     Big
    1.02
    BIG
    1.01
    Big
    0.98
     Biggs
    0.91
     Bigelow
    0.86
     impractica
    0.86
     viciss
    0.82
    Activations Density 0.112%

    No Known Activations