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. 15072
    Prev
    Next
    INDEX
    Explanations

    economic terms related to products

    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
    1870
    +0.15
    0.6%
    1339
    +0.14
    0.6%
    553
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1339
    +0.15
    0.03
    553
    +0.14
    0.03
    2036
    +0.13
    0.03
    Negative Logits
     sergio
    -0.91
     itemName
    -0.79
     affor
    -0.77
     leonardo
    -0.77
     fep
    -0.76
     gabri
    -0.75
     noOf
    -0.75
     jorge
    -0.74
     lyon
    -0.74
     javier
    -0.74
    POSITIVE LOGITS
     product
    1.33
    product
    1.28
     Product
    1.25
     products
    1.24
    Product
    1.19
     Products
    1.14
    products
    1.12
    PRODUCT
    1.07
     PRODUCT
    1.07
    Products
    1.04
    Activations Density 0.070%

    No Known Activations