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. 972
    Prev
    Next
    INDEX
    Explanations

    phrases related to inequality and imbalance in social contexts

    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
    +0.18
    0.7%
    1141
    +0.11
    0.4%
    2016
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2016
    +0.18
    0.03
    647
    +0.11
    0.03
    74
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.00
     intersper
    -1.00
    /***
    
    -0.99
    
    
    -0.83
    ⓧ
    -0.82
    <?
    -0.72
     acquaint
    -0.71
     interposed
    -0.68
     endow
    -0.68
    /*!
    
    -0.67
    POSITIVE LOGITS
     riva
    1.03
     marea
    0.99
     borsa
    0.98
     signora
    0.94
     giustizia
    0.93
     paradiso
    0.91
     fabbrica
    0.91
     conflic
    0.91
     montagna
    0.90
     lepro
    0.90
    Activations Density 0.210%

    No Known Activations