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. 15540
    Prev
    Next
    INDEX
    Explanations

    the word "everyone" in various contexts

    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
    25
    +0.12
    0.4%
    1910
    +0.10
    0.3%
    1671
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.12
    0.05
    1910
    +0.10
    0.04
    1671
    +0.10
    0.04
    Negative Logits
     répon
    -0.76
     empêche
    -0.64
     exé
    -0.62
     serons
    -0.62
     prouve
    -0.60
    Noice
    -0.60
     susc
    -0.59
     obé
    -0.58
     venons
    -0.58
    Flashcards
    -0.58
    POSITIVE LOGITS
     everyone
    0.97
     Everyone
    0.95
    everyone
    0.94
    Everyone
    0.92
     everybody
    0.88
     EVERYONE
    0.86
    Everybody
    0.85
     Everybody
    0.84
     else
    0.79
     everywhere
    0.78
    Activations Density 0.102%

    No Known Activations