Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 766
    Prev
    Next
    INDEX
    Explanations

    references to age and demographic descriptors related to people

    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
    +0.22
    0.8%
    1081
    +0.10
    0.4%
    554
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1081
    +0.22
    0.04
    1033
    +0.10
    0.04
    1443
    +0.08
    0.03
    Negative Logits
    <bos>
    -1.90
    ⓧ
    -0.73
    /***
    
    -0.69
    <?
    
    -0.67
     intersper
    -0.67
     poveznice
    -0.62
    <!--
    
    -0.62
    ///**
    -0.61
    /**
    -0.56
     gynnwys
    -0.54
    POSITIVE LOGITS
     elderly
    0.96
     Palembang
    0.89
     aging
    0.88
     aged
    0.82
     Jambi
    0.82
     ageing
    0.81
     pensioners
    0.77
     bandung
    0.77
     retirement
    0.77
     Minang
    0.76
    Activations Density 0.317%

    No Known Activations