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. 1219
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional responses and reflections

    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
    +0.25
    0.9%
    381
    +0.12
    0.4%
    198
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.25
    0.03
    381
    +0.12
    0.02
    184
    +0.11
    0.01
    Negative Logits
    <bos>
    -1.73
    <>
    
    -0.64
    contentLoaded
    -0.61
    titleMargin
    -0.57
    ///**
    -0.55
     /**
    
    -0.54
    /***
    
    -0.53
    PositiveButton
    -0.53
    ukone
    -0.52
    Inflater
    -0.51
    POSITIVE LOGITS
     viciss
    1.17
     practition
    1.12
     reluct
    1.06
     errone
    1.02
     haer
    1.01
     aen
    0.95
     accla
    0.94
     feen
    0.93
     thut
    0.92
     sovere
    0.92
    Activations Density 0.222%

    No Known Activations