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. 685
    Prev
    Next
    INDEX
    Explanations

    terms related to unconsciousness or loss of consciousness

    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%
    1013
    +0.10
    0.3%
    946
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.23
    0.05
    1553
    +0.10
    0.05
    736
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.04
    HasAnnotation
    -0.64
    SharedDtor
    -0.57
    Buildable
    -0.57
    ClientSize
    -0.56
    contentLoaded
    -0.55
     autorytatywna
    -0.54
    FieldBuilder
    -0.54
    ///**
    -0.53
    ///</
    -0.51
    POSITIVE LOGITS
     unlaw
    0.95
     Middles
    0.94
     pamph
    0.93
     Glou
    0.92
     Vaugh
    0.89
     Confu
    0.88
     chrysler
    0.86
     McLaugh
    0.85
     McInt
    0.85
     tucson
    0.83
    Activations Density 0.272%

    No Known Activations