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. 1023
    Prev
    Next
    INDEX
    Explanations

    punctuations and other formatting symbols related to document structure

    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
    +0.27
    1.4%
    1438
    +0.08
    0.4%
    1133
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    973
    +0.27
    0.08
    1133
    +0.08
    0.07
    1096
    +0.08
    0.07
    Negative Logits
    <bos>
    -2.69
    ⓧ
    -1.13
    /**
    -1.10
    
    
    -1.02
    <?
    -0.93
    /*
    -0.85
     springfox
    -0.80
    /*!
    
    -0.70
    /***
    
    -0.64
    <?
    
    -0.62
    POSITIVE LOGITS
     lele
    1.14
     roul
    1.09
     seksi
    1.02
     cæ
    1.01
     bandung
    1.01
     salu
    1.00
     incess
    0.98
     mû
    0.98
     thuy
    0.97
     jawa
    0.97
    Activations Density 0.078%

    No Known Activations