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. 15544
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of meat or meat-related products

    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
    421
    +0.17
    0.6%
    896
    +0.15
    0.5%
    866
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    421
    +0.17
    0.03
    896
    +0.15
    0.03
    489
    +0.12
    0.02
    Negative Logits
     autorytatywna
    -0.65
     Obrador
    -0.55
    zwald
    -0.51
    GEBURTSDATUM
    -0.49
    Bibliograf
    -0.47
     Göttingen
    -0.47
    cauciones
    -0.47
     Paroles
    -0.47
    openqa
    -0.46
     Geophysics
    -0.45
    POSITIVE LOGITS
     meat
    1.29
    meat
    1.15
     MEAT
    1.06
    Meat
    1.05
     Meat
    1.04
     meats
    1.01
     beef
    0.84
    beef
    0.76
    Beef
    0.69
     Beef
    0.63
    Activations Density 0.105%

    No Known Activations