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. 6891
    Prev
    Next
    INDEX
    Explanations

    instances and variations of the word "structure" 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.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
    +0.25
    1.6%
    554
    +0.15
    1.0%
    1870
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    554
    +0.25
    0.04
    251
    +0.15
    0.03
    25
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.64
    ⓧ
    -0.95
    /***
    
    -0.77
    Identyfik
    -0.65
    /*!
    
    -0.64
     rehabilitate
    -0.64
    ///**
    -0.60
    /**
    -0.58
     avert
    -0.57
     expel
    -0.57
    POSITIVE LOGITS
     lele
    1.23
     thut
    1.12
     fua
    1.09
     bandung
    1.08
     Structure
    1.07
     structure
    1.04
     thuy
    1.03
     estruct
    1.01
    Structure
    1.01
     Minang
    1.01
    Activations Density 0.037%

    No Known Activations