Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 809
    Prev
    Next
    INDEX
    Explanations

    names of individuals and social media handles

    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
    +0.22
    0.8%
    1343
    +0.19
    0.7%
    227
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.22
    0.05
    1275
    +0.19
    0.04
    1097
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.45
    ⓧ
    -1.01
    Autoritní
    -0.80
    /**
    -0.78
    <?
    -0.75
    
    
    -0.74
    GEBURTSDATUM
    -0.72
    RegressionTest
    -0.68
    Panamoan
    -0.62
    intios
    -0.61
    POSITIVE LOGITS
     accla
    1.05
     saar
    1.02
     kristal
    0.99
     vne
    0.98
     kram
    0.97
     silikon
    0.94
     Minang
    0.94
     makro
    0.94
     Strukt
    0.94
     keramik
    0.93
    Activations Density 0.053%

    No Known Activations