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. 15150
    Prev
    Next
    INDEX
    Explanations

    pronouns related to gender

    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
    397
    +0.11
    0.4%
    1637
    +0.11
    0.3%
    2011
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.11
    0.07
    397
    +0.11
    0.07
    1637
    +0.10
    0.08
    Negative Logits
     suspic
    -1.23
     thut
    -1.23
     gend
    -1.22
     tew
    -1.18
     seiz
    -1.17
     fta
    -1.17
     sii
    -1.17
     aen
    -1.15
     desir
    -1.11
     stockholm
    -1.11
    POSITIVE LOGITS
     himself
    1.09
    His
    1.09
    his
    1.03
     his
    1.00
    himself
    1.00
     His
    0.99
    He
    0.96
     Himself
    0.93
     He
    0.92
     he
    0.88
    Activations Density 0.558%

    No Known Activations