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. 3066
    Prev
    Next
    INDEX
    Explanations

    information related to esports tournaments

    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
    81
    +0.16
    0.5%
    1499
    +0.12
    0.4%
    455
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.16
    0.06
    1551
    +0.12
    0.06
    455
    +0.12
    0.03
    Negative Logits
    asının
    -0.69
    ăți
    -0.59
    wohnung
    -0.58
    fillText
    -0.58
    SdkVersion
    -0.58
    Trimethyl
    -0.57
     quadrinhos
    -0.57
    Grüße
    -0.57
    Vielleicht
    -0.56
    Dimethyl
    -0.56
    POSITIVE LOGITS
     hcm
    1.55
     inev
    1.49
     maneu
    1.45
     emphat
    1.45
     fta
    1.45
     volunte
    1.45
     intersper
    1.45
     reluct
    1.43
     resear
    1.43
     accla
    1.42
    Activations Density 0.714%

    No Known Activations