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. 8406
    Prev
    Next
    INDEX
    Explanations

    references to book publishing, funding methods for games, and crowdfunding platforms

    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
    1661
    +0.11
    0.3%
    1403
    +0.08
    0.2%
    684
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1901
    +0.11
    0.03
    1661
    +0.08
    0.03
    1038
    +0.07
    0.03
    Negative Logits
     Traité
    -0.90
     Gouvernement
    -0.88
     Secrétaire
    -0.85
     Messieurs
    -0.83
     Mémoires
    -0.83
     Præ
    -0.83
     fatis
    -0.80
     Ministre
    -0.77
     Sén
    -0.76
     Église
    -0.75
    POSITIVE LOGITS
    <bos>
    0.77
     publicity
    0.65
     marketing
    0.61
     Publicity
    0.59
     promotion
    0.59
     Normdatei
    0.56
     sales
    0.56
    xase
    0.52
     sell
    0.52
     visibility
    0.52
    Activations Density 0.394%

    No Known Activations