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. 6795
    Prev
    Next
    INDEX
    Explanations

    specific terms related to technology, politics, and social issues

    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
    1842
    +0.20
    0.8%
    50
    +0.16
    0.6%
    1870
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.20
    0.10
    1870
    +0.16
    0.06
    1842
    +0.15
    0.05
    Negative Logits
    <bos>
    -2.67
    StoreMessageInfo
    -0.88
    /**
    -0.81
    ⓧ
    -0.78
     שוליים
    -0.77
     tartalomajánló
    -0.76
    <?
    -0.75
    aarrggbb
    -0.74
    
    
    -0.74
    /*++
    -0.73
    POSITIVE LOGITS
     Minang
    1.60
     aen
    1.55
     hcm
    1.55
     emphat
    1.52
     bandung
    1.52
     mef
    1.49
     wien
    1.46
     lele
    1.46
     salomon
    1.43
     meis
    1.42
    Activations Density 0.863%

    No Known Activations