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. 1692
    Prev
    Next
    INDEX
    Explanations

    the presence of technical terms or jargon related to websites, search results, and user experience

    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
    674
    +0.16
    0.5%
    1843
    +0.10
    0.3%
    511
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.16
    0.05
    1919
    +0.10
    0.06
    1843
    +0.09
    0.04
    Negative Logits
     Coim
    -0.92
     McLaugh
    -0.91
     Vaugh
    -0.91
     Augu
    -0.85
     Penna
    -0.80
     McInt
    -0.80
     Thos
    -0.79
     Juf
    -0.77
     Rine
    -0.76
     Bartholo
    -0.76
    POSITIVE LOGITS
    <bos>
    1.25
     reading
    0.77
     read
    0.75
    reading
    0.71
     READING
    0.68
    read
    0.67
     digest
    0.65
     reads
    0.57
    reader
    0.57
     READ
    0.56
    Activations Density 0.538%

    No Known Activations