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. 6761
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage in sentences

    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
    1.2%
    382
    +0.14
    0.6%
    2034
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.27
    0.13
    2034
    +0.14
    0.12
    2019
    +0.13
    0.09
    Negative Logits
    <bos>
    -2.89
    /***
    
    -1.04
    ///**
    -0.99
    <?
    -0.84
    ⓧ
    -0.84
    /**
    -0.81
    //*/
    -0.76
     intersper
    -0.76
     /**
    
    -0.76
     disbur
    -0.75
    POSITIVE LOGITS
     marea
    0.73
     materie
    0.70
     seksi
    0.66
     véhic
    0.66
     depoz
    0.66
     ados
    0.65
     poliester
    0.65
     momente
    0.64
     InkWell
    0.62
    celona
    0.61
    Activations Density 0.680%

    No Known Activations