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. 1827
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant contributions or roles played by individuals or groups

    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
    +0.20
    0.8%
    1618
    +0.15
    0.6%
    1124
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1618
    +0.20
    0.06
    1124
    +0.15
    0.05
    1778
    +0.14
    0.04
    Negative Logits
    <bos>
    -2.10
    //{
    
    -0.61
    toPromise
    -0.57
    //};
    -0.56
    ///**
    -0.55
    ites
    -0.54
    /***
    
    -0.53
    ́
    -0.53
     државе
    -0.52
    зулта
    -0.52
    POSITIVE LOGITS
     increa
    1.42
     affor
    1.38
     wherea
    1.38
     swarovski
    1.34
     guarante
    1.34
     ecru
    1.33
     stockholm
    1.30
     lola
    1.30
     unden
    1.30
     peppa
    1.30
    Activations Density 0.137%

    No Known Activations