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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15007
    Prev
    Next
    INDEX
    Explanations

    names of individuals, specifically women, with the title "Mrs."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    544
    +0.13
    0.4%
    1527
    +0.13
    0.4%
    1964
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1527
    +0.13
    0.01
    544
    +0.13
    0.01
    1964
    +0.11
    0.01
    Negative Logits
    unisex
    -0.56
    ">“
    -0.51
    cardigan
    -0.50
     internas
    -0.50
     letti
    -0.48
    Dishwasher
    -0.48
    satin
    -0.47
     проєкту
    -0.46
    charcoal
    -0.46
    crochet
    -0.46
    POSITIVE LOGITS
     Mrs
    1.26
    Mrs
    1.21
     MRS
    0.99
     mrs
    0.92
    MRS
    0.83
    mrs
    0.81
     höl
    0.72
     Meksi
    0.72
     Chapitre
    0.71
     Mexique
    0.70
    Activations Density 0.025%

    No Known Activations