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. 1796
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms related to contracts and agreements

    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
    1499
    +0.20
    0.9%
    50
    +0.17
    0.8%
    1177
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.20
    0.16
    1553
    +0.17
    0.13
    1120
    +0.15
    0.02
    Negative Logits
    <bos>
    -2.14
    ⓧ
    -0.93
    /**
    -0.92
    
    
    -0.90
    <?
    -0.87
    Fordítás
    -0.85
    noStroke
    -0.84
    źródło
    -0.81
    vece
    -0.80
    senza
    -0.80
    POSITIVE LOGITS
     saar
    1.74
     lele
    1.70
     keramik
    1.61
     silikon
    1.60
     kaos
    1.57
     maksi
    1.52
     kafe
    1.51
     Nö
    1.50
     seksi
    1.50
     torba
    1.50
    Activations Density 2.717%

    No Known Activations