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. 15316
    Prev
    Next
    INDEX
    Explanations

    adverbs of degree or emphasis

    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
    227
    +0.11
    0.3%
    1778
    +0.09
    0.3%
    1473
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.11
    0.05
    1194
    +0.09
    0.03
    1052
    +0.09
    0.04
    Negative Logits
     Mejía
    -0.77
     Áng
    -0.69
     Ávila
    -0.68
     Méndez
    -0.66
     Cuer
    -0.66
     Cuen
    -0.65
     Bahía
    -0.65
     Cár
    -0.62
     Hierro
    -0.62
     Almería
    -0.62
    POSITIVE LOGITS
     faggot
    0.65
     sherpa
    0.62
     ugg
    0.62
     AppColors
    0.61
     stit
    0.61
     volete
    0.61
     intermitt
    0.60
     disreg
    0.59
     legging
    0.58
     vogli
    0.57
    Activations Density 0.090%

    No Known Activations