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. 338
    Prev
    Next
    INDEX
    Explanations

    technical instructions or steps

    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
    1699
    +0.13
    0.4%
    776
    +0.09
    0.3%
    1108
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    353
    +0.13
    0.03
    1900
    +0.09
    0.02
    1835
    +0.09
    0.02
    Negative Logits
     rascal
    -0.77
     feen
    -0.76
     ftre
    -0.72
    FTFY
    -0.71
     foon
    -0.70
     bave
    -0.70
     defire
    -0.69
     shenan
    -0.68
     hentai
    -0.68
     vagu
    -0.68
    POSITIVE LOGITS
     sedia
    0.71
     balon
    0.69
     bunda
    0.63
    mavi
    0.61
    sune
    0.60
     ananas
    0.59
     kedi
    0.59
     mús
    0.59
     espri
    0.58
    masin
    0.57
    Activations Density 0.049%

    No Known Activations