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. 387
    Prev
    Next
    INDEX
    Explanations

    references to a specific female pronoun

    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
    381
    +0.13
    0.4%
    1937
    +0.12
    0.4%
    331
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.13
    0.09
    331
    +0.12
    0.07
    521
    +0.12
    0.05
    Negative Logits
     brille
    -0.88
     affez
    -0.84
     trouva
    -0.78
     persil
    -0.77
     agrico
    -0.75
     svin
    -0.73
     fré
    -0.73
     LIRE
    -0.72
     vinil
    -0.72
     pietre
    -0.72
    POSITIVE LOGITS
     herself
    1.35
     she
    1.30
    herself
    1.18
    she
    1.16
    She
    1.14
     shes
    1.07
     her
    1.06
     She
    1.03
     hers
    0.92
    حياتها
    0.90
    Activations Density 0.159%

    No Known Activations