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. 1088
    Prev
    Next
    INDEX
    Explanations

    names of sports teams or athletic organizations

    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
    1177
    +0.12
    0.4%
    227
    +0.11
    0.4%
    50
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.12
    0.04
    1905
    +0.11
    0.03
    782
    +0.10
    0.03
    Negative Logits
    <bos>
    -1.74
    /**
    -0.88
    
    
    -0.85
    /***
    
    -0.82
    ⓧ
    -0.78
    <?
    -0.78
    nasel
    -0.76
    /*
    -0.72
     DEFENDANT
    -0.70
    <?
    
    -0.70
    POSITIVE LOGITS
     Khart
    1.46
     kosme
    1.45
     akut
    1.44
     panik
    1.44
     maksi
    1.39
     Kategor
    1.36
     praktik
    1.32
     konserv
    1.30
     seksi
    1.29
     keramik
    1.27
    Activations Density 0.147%

    No Known Activations