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. 119
    Prev
    Next
    INDEX
    Explanations

    multiplayer gaming-related terms and terminology

    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
    599
    +0.14
    0.4%
    678
    +0.13
    0.4%
    304
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.14
    0.04
    270
    +0.13
    0.03
    1755
    +0.11
    0.02
    Negative Logits
    <bos>
    -0.61
     salic
    -0.56
     dignité
    -0.56
     Agrega
    -0.51
     tolu
    -0.50
    webElementGuid
    -0.47
    Descripció
    -0.46
    Phenyl
    -0.46
     aldehyde
    -0.46
    Fordítás
    -0.45
    POSITIVE LOGITS
     multiplayer
    0.84
     impra
    0.74
     indestru
    0.70
     Teamwork
    0.67
     intersper
    0.67
     overcrow
    0.66
     ineffec
    0.63
     cushi
    0.61
     lapto
    0.61
     bandeau
    0.61
    Activations Density 0.221%

    No Known Activations