© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 4101
    Prev
    Next
    INDEX
    Explanations

    statements made by people regarding various situations and opinions

    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
    2019
    +0.29
    1.0%
    381
    +0.22
    0.8%
    605
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.29
    0.05
    924
    +0.22
    0.05
    605
    +0.13
    0.02
    Negative Logits
     casio
    -0.84
     Godt
    -0.75
     waifu
    -0.75
     îna
    -0.72
     hentai
    -0.72
     lasciato
    -0.72
    Whoo
    -0.71
     intermitt
    -0.70
    FTFY
    -0.70
    Czym
    -0.70
    POSITIVE LOGITS
    But
    0.92
    Therefore
    0.91
    We
    0.89
    However
    0.87
    It
    0.86
    If
    0.86
    Then
    0.85
    This
    0.83
    There
    0.81
    They
    0.79
    Activations Density 0.138%

    No Known Activations