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. 955
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to income eligibility and federal poverty metrics

    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
    +0.20
    0.7%
    1842
    +0.17
    0.6%
    1253
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.20
    0.06
    1385
    +0.17
    0.06
    615
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.15
    
    
    -1.17
    ⓧ
    -1.06
    /**
    -1.03
    <?
    -0.97
    /*
    -0.91
    <?
    
    -0.74
     inaugurate
    -0.63
     strode
    -0.62
     intersper
    -0.61
    POSITIVE LOGITS
     bandung
    1.15
     jawa
    1.01
     maroc
    0.96
     kafe
    0.94
     ados
    0.91
     Minang
    0.90
     Karang
    0.90
    capulco
    0.89
     Jambi
    0.86
     surabaya
    0.86
    Activations Density 0.324%

    No Known Activations