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. 539
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing societal issues 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
    1757
    +0.13
    0.4%
    866
    +0.12
    0.4%
    1573
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1573
    +0.13
    0.04
    1983
    +0.12
    0.04
    866
    +0.11
    0.03
    Negative Logits
     Läs
    -0.49
    zaba
    -0.49
     kosme
    -0.46
    Dele
    -0.46
    Appendices
    -0.44
     Vgl
    -0.44
    Puri
    -0.44
     hormon
    -0.43
    Bin
    -0.43
    resulting
    -0.42
    POSITIVE LOGITS
     about
    0.78
     ABOUT
    0.77
     About
    0.72
    ABOUT
    0.70
    bouts
    0.68
    about
    0.67
     discussing
    0.64
    uests
    0.62
    About
    0.62
    antity
    0.61
    Activations Density 0.160%

    No Known Activations