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. 832
    Prev
    Next
    INDEX
    Explanations

    references to cultural standards and perceptions of beauty

    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%
    1978
    +0.11
    0.4%
    378
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    581
    +0.18
    0.09
    378
    +0.11
    0.09
    1055
    +0.10
    0.07
    Negative Logits
    <bos>
    -2.18
     intersper
    -0.61
     enshr
    -0.57
     amass
    -0.54
    //---
    -0.53
    /***
    
    -0.53
     condense
    -0.52
     tentatively
    -0.52
     defray
    -0.51
     harmonize
    -0.51
    POSITIVE LOGITS
     anymore
    0.99
     signora
    0.92
     bandung
    0.91
     quoique
    0.82
     nor
    0.81
    postolic
    0.81
     tristes
    0.80
     warung
    0.79
     jawa
    0.78
    quarelle
    0.77
    Activations Density 1.232%

    No Known Activations