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. 1128
    Prev
    Next
    INDEX
    Explanations

    concepts related to political correctness and performance-driven behaviors

    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
    +0.28
    1.0%
    198
    +0.10
    0.4%
    1978
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    804
    +0.28
    0.06
    1368
    +0.10
    0.04
    515
    +0.07
    0.05
    Negative Logits
    <bos>
    -2.33
    /***
    
    -0.95
    /*!
    
    -0.70
    ⓧ
    -0.61
     intersper
    -0.60
    
    
    -0.60
     ratify
    -0.56
     inaugurate
    -0.55
     enshr
    -0.54
    дём
    -0.54
    POSITIVE LOGITS
     paradiso
    1.17
     riva
    1.12
     maroc
    1.06
     soggior
    1.05
     signora
    1.02
     palio
    1.01
     bosco
    0.95
     swarovski
    0.94
     croce
    0.93
     particolar
    0.93
    Activations Density 1.092%

    No Known Activations