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. 204
    Prev
    Next
    INDEX
    Explanations

    numerical mentions, specifically focusing on occurrences of the word "number" followed by a numeric value

    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
    1137
    +0.11
    0.3%
    971
    +0.10
    0.3%
    1363
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1137
    +0.11
    0.04
    537
    +0.10
    0.03
    961
    +0.10
    0.03
    Negative Logits
     intermitt
    -1.16
     madonna
    -1.13
     perfet
    -1.06
     impra
    -1.06
     accla
    -1.05
     embra
    -1.03
     vagab
    -1.01
     intersper
    -1.01
     secon
    -1.00
     reluct
    -0.99
    POSITIVE LOGITS
     number
    1.17
    number
    1.11
    Number
    1.01
     Number
    0.96
     NUMBER
    0.89
    NUMBER
    0.88
     num
    0.86
     numbers
    0.86
     número
    0.85
    num
    0.83
    Activations Density 0.068%

    No Known Activations