© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 291
    Prev
    Next
    INDEX
    Explanations

    the word "should" in various contexts related to obligations or recommendations

    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
    +0.29
    1.7%
    680
    +0.14
    0.8%
    1328
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.29
    0.06
    1328
    +0.14
    0.06
    680
    +0.13
    0.06
    Negative Logits
    <bos>
    -2.42
     endow
    -0.79
    /***
    -0.75
    ⓧ
    -0.74
     intersper
    -0.72
     amass
    -0.71
    
    -0.69
     defray
    -0.66
     gratify
    -0.64
     disarm
    -0.63
    POSITIVE LOGITS
    should
    0.87
     Should
    0.87
     should
    0.86
     SHOULD
    0.83
    Should
    0.82
    hould
    0.80
     soggior
    0.78
     chiunque
    0.75
     purtroppo
    0.74
     cammin
    0.70
    Activations Density 0.091%

    No Known Activations