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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 810
    Prev
    Next
    INDEX
    Explanations

    time and date references in a document

    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
    +0.30
    1.1%
    1343
    +0.16
    0.6%
    1699
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.30
    0.05
    1190
    +0.16
    0.04
    609
    +0.07
    0.04
    Negative Logits
    <bos>
    -2.71
    ⓧ
    -0.85
    Vegeu
    -0.74
    <>
    
    -0.71
    /**
    -0.67
    <?
    -0.65
     encontraban
    -0.65
    /*
    -0.64
     endforeach
    -0.63
    glMatrixMode
    -0.62
    POSITIVE LOGITS
     resear
    1.38
     practition
    1.29
     accla
    1.29
     affor
    1.28
     Keny
    1.25
     maneu
    1.23
     reluct
    1.20
     unlaw
    1.19
     philanth
    1.19
     Manufact
    1.19
    Activations Density 0.075%

    No Known Activations