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. 1789
    Prev
    Next
    INDEX
    Explanations

    punctuations and sentence endings in complex arguments

    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
    1535
    +0.27
    1.5%
    382
    +0.20
    1.1%
    50
    +0.19
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.27
    0.20
    1535
    +0.20
    0.15
    2034
    +0.19
    0.17
    Negative Logits
    <bos>
    -2.62
    ⓧ
    -0.94
    ///**
    -0.84
    /***
    
    -0.80
    /**
    -0.75
    
    
    -0.71
    <?
    -0.71
     springfox
    -0.68
     ventr
    -0.66
    /*
    -0.63
    POSITIVE LOGITS
     épu
    1.07
     clô
    0.99
     véhic
    0.98
    mavi
    0.97
     marea
    0.97
     écout
    0.95
     soulign
    0.95
     alté
    0.94
     maroc
    0.91
     malheureux
    0.90
    Activations Density 1.090%

    No Known Activations