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. 844
    Prev
    Next
    INDEX
    Explanations

    expressions of fatigue or frustration

    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
    0.9%
    1235
    +0.09
    0.3%
    991
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1476
    +0.25
    0.02
    1235
    +0.09
    0.02
    1852
    +0.08
    0.02
    Negative Logits
    <bos>
    -2.68
    /***
    
    -0.68
    ⓧ
    -0.66
    ///**
    -0.62
    /**
    -0.59
    
    
    -0.58
    require
    -0.55
    beforeAll
    -0.54
    Controllo
    -0.52
     autorytatywna
    -0.52
    POSITIVE LOGITS
     riviera
    1.13
     toledo
    1.09
     frankfurt
    1.06
     tramont
    1.03
     verona
    1.02
     venice
    1.01
     Juf
    0.99
     eiffel
    0.99
     leonardo
    0.99
     ibiza
    0.99
    Activations Density 0.127%

    No Known Activations