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. 1483
    Prev
    Next
    INDEX
    Explanations

    recipes and cooking instructions

    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
    +0.27
    0.8%
    1535
    +0.12
    0.4%
    304
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.27
    0.03
    924
    +0.12
    0.03
    946
    +0.10
    0.03
    Negative Logits
    Może
    -0.81
    Și
    -0.71
    Gdy
    -0.71
    Dlaczego
    -0.68
     Zwar
    -0.67
    amaged
    -0.64
    Kiedy
    -0.62
    Incluso
    -0.61
    Czym
    -0.60
    Wię
    -0.60
    POSITIVE LOGITS
     lele
    1.40
     istan
    1.38
     hina
    1.31
     embra
    1.30
     dispen
    1.26
     mef
    1.26
     salu
    1.23
     ordina
    1.23
     hej
    1.23
     alkoh
    1.20
    Activations Density 0.055%

    No Known Activations