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. 6848
    Prev
    Next
    INDEX
    Explanations

    instances of the word "become" or its variations, indicating a focus on transformation or change

    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
    +0.27
    1.6%
    1909
    +0.16
    0.9%
    478
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1909
    +0.27
    0.07
    966
    +0.16
    0.06
    1562
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.70
    str
    -0.72
    map
    -0.70
    bar
    -0.67
    ///
    -0.65
    public
    -0.65
    array
    -0.64
    //
    -0.63
    Map
    -0.63
     Paris
    -0.63
    POSITIVE LOGITS
     jaya
    1.75
     lamborghini
    1.61
     wien
    1.61
     hairc
    1.59
     volunte
    1.59
     tupperware
    1.58
     swarovski
    1.58
     scrat
    1.55
     increa
    1.54
     ankara
    1.54
    Activations Density 0.101%

    No Known Activations