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. 13626
    Prev
    Next
    INDEX
    Explanations

    references to the location "Oklahoma City" and related sports teams such as the "Thunder."

    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
    597
    +0.13
    0.6%
    172
    +0.13
    0.6%
    596
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1233
    +0.13
    0.02
    1516
    +0.13
    0.02
    1077
    +0.13
    0.03
    Negative Logits
     مرئيه
    -0.66
    ESSOR
    -0.47
    viro
    -0.44
    leece
    -0.44
    valbard
    -0.43
    Lorsque
    -0.42
     cranberries
    -0.42
    Beaucoup
    -0.42
    Рас
    -0.42
     Cámara
    -0.42
    POSITIVE LOGITS
     Oklahoma
    1.20
    Oklahoma
    1.10
     Okla
    1.00
     OK
    0.92
     Ok
    0.89
     Docteur
    0.88
     pavillon
    0.87
     Secrétaire
    0.83
    OK
    0.81
    Ok
    0.80
    Activations Density 0.118%

    No Known Activations