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. 981
    Prev
    Next
    INDEX
    Explanations

    the presence of the article "a" in various contexts

    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
    +0.40
    2.0%
    1896
    +0.15
    0.7%
    1984
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.40
    0.13
    1896
    +0.15
    0.09
    1034
    +0.14
    0.10
    Negative Logits
    <bos>
    -2.79
     découvre
    -0.66
     jette
    -0.62
     ressemble
    -0.59
     préfère
    -0.59
    ///**
    -0.57
     croit
    -0.56
     confiable
    -0.56
     réalise
    -0.56
     prouve
    -0.53
    POSITIVE LOGITS
     conflic
    0.94
     considér
    0.92
     unlaw
    0.91
     sappi
    0.88
     Keny
    0.85
     Compañ
    0.84
     soulign
    0.84
     véhic
    0.83
     marea
    0.82
     valencia
    0.82
    Activations Density 0.645%

    No Known Activations