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. 1299
    Prev
    Next
    INDEX
    Explanations

    numerical quantities mentioned in a text

    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
    1994
    +0.11
    0.3%
    971
    +0.10
    0.3%
    1535
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1994
    +0.11
    0.03
    1
    +0.10
    0.04
    220
    +0.10
    0.03
    Negative Logits
     Sén
    -0.53
     Karang
    -0.50
     Flamengo
    -0.50
     Olimpia
    -0.50
     Tahu
    -0.49
     Piso
    -0.48
     Levante
    -0.48
     palla
    -0.47
     Palmeiras
    -0.47
     Rossa
    -0.47
    POSITIVE LOGITS
     number
    0.82
    number
    0.76
     Number
    0.67
    Number
    0.65
     NUMBER
    0.65
    NUMBER
    0.62
    ValueStyle
    0.61
    PerformLayout
    0.60
    getNumber
    0.59
     número
    0.56
    Activations Density 0.059%

    No Known Activations