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. 1086
    Prev
    Next
    INDEX
    Explanations

    subordinate clauses or phrases that provide additional information or context

    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
    +0.35
    1.8%
    1967
    +0.12
    0.6%
    2034
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.35
    0.08
    382
    +0.12
    0.07
    2034
    +0.12
    0.08
    Negative Logits
    <bos>
    -3.16
    ⓧ
    -1.17
    <?
    -1.14
    /***
    
    -0.99
    
    
    -0.88
    ///**
    -0.79
    //};
    -0.79
    //*/
    -0.78
    //});
    -0.78
    <?
    
    -0.78
    POSITIVE LOGITS
     marea
    0.66
     Czechos
    0.65
     cartier
    0.65
     unspeak
    0.63
    antastic
    0.63
     pollut
    0.62
     gaily
    0.62
     maneu
    0.61
     Inhabitants
    0.59
     accla
    0.56
    Activations Density 0.408%

    No Known Activations