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. 634
    Prev
    Next
    INDEX
    Explanations

    references to the city of Austin, Texas

    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
    479
    +0.17
    0.8%
    1350
    +0.14
    0.6%
    241
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.17
    0.04
    981
    +0.14
    0.04
    1177
    +0.12
    0.02
    Negative Logits
     autunno
    -0.62
     kerala
    -0.61
     Susquehanna
    -0.56
    Referencie
    -0.52
     Keyes
    -0.51
     Shreve
    -0.51
    více
    -0.47
     dzī
    -0.47
    évalu
    -0.47
     հղումներ
    -0.47
    POSITIVE LOGITS
     Austin
    1.04
    Austin
    0.97
     Gordon
    0.85
     AUSTIN
    0.82
    Gordon
    0.81
    USTIN
    0.79
     Lég
    0.78
     Chapitre
    0.76
     Câ
    0.75
    austin
    0.72
    Activations Density 0.210%

    No Known Activations