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. 656
    Prev
    Next
    INDEX
    Explanations

    words related to fibers, materials, and medical conditions involving fibers

    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
    897
    +0.15
    0.7%
    1757
    +0.15
    0.7%
    1265
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1137
    +0.15
    0.05
    1363
    +0.15
    0.04
    976
    +0.14
    0.04
    Negative Logits
    Ehh
    -0.61
    FTFY
    -0.57
     citoy
    -0.56
    Hahah
    -0.55
     JULIO
    -0.54
     Dica
    -0.54
    Lmfao
    -0.53
     HERBERT
    -0.52
     něko
    -0.51
     stabilis
    -0.50
    POSITIVE LOGITS
    ized
    0.81
     fiber
    0.76
    ization
    0.76
     læng
    0.75
     fibers
    0.74
     neighborhood
    0.73
    anță
    0.73
    izing
    0.73
    hitheater
    0.72
     neighborhoods
    0.71
    Activations Density 0.342%

    No Known Activations