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. 6774
    Prev
    Next
    INDEX
    Explanations

    the word "no" in various contexts

    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
    +0.28
    1.5%
    1262
    +0.14
    0.7%
    1124
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1124
    +0.28
    0.07
    1262
    +0.14
    0.07
    1562
    +0.12
    0.06
    Negative Logits
    <bos>
    -2.25
    /***
    
    -0.68
    //};
    -0.64
     shivered
    -0.63
    <!--
    
    -0.61
     shuddered
    -0.60
     leaped
    -0.58
     strode
    -0.56
    })();
    
    -0.56
    ///**
    -0.56
    POSITIVE LOGITS
     gabri
    0.92
     remonte
    0.88
     guatemala
    0.87
     valencia
    0.86
     sergio
    0.85
     préc
    0.85
     viciss
    0.85
     ricardo
    0.82
     no
    0.82
     javier
    0.81
    Activations Density 0.129%

    No Known Activations