Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2318
    Prev
    Next
    INDEX
    Explanations

    the word "Yes" used in different contexts

    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
    517
    +0.13
    0.5%
    1527
    +0.12
    0.4%
    1671
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    851
    +0.13
    0.03
    1527
    +0.12
    0.03
    517
    +0.11
    0.02
    Negative Logits
    InkWell
    -0.72
     outubro
    -0.63
     Septiembre
    -0.58
    πάρχ
    -0.57
     Noviembre
    -0.56
    */
    
    
    -0.55
     Diciembre
    -0.55
     fevereiro
    -0.55
    Aucun
    -0.54
    TextFormField
    -0.54
    POSITIVE LOGITS
     shenan
    1.17
     scrat
    1.11
     disagre
    1.10
     disreg
    1.10
     cushi
    1.08
     maneu
    1.07
     milf
    1.06
     suscep
    1.06
     unspeak
    1.06
     hairc
    1.03
    Activations Density 0.038%

    No Known Activations