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. 1406
    Prev
    Next
    INDEX
    Explanations

    information related to medical conditions, specifically heart attacks and marijuana use

    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
    1581
    +0.12
    0.4%
    1978
    +0.11
    0.4%
    577
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    147
    +0.12
    0.03
    161
    +0.11
    0.03
    1581
    +0.10
    0.03
    Negative Logits
     earnestness
    -0.65
     noblest
    -0.59
     shenan
    -0.59
     caprice
    -0.59
     unspeak
    -0.59
     poetical
    -0.58
     liberality
    -0.57
     Lbs
    -0.57
     impet
    -0.56
     unwarran
    -0.56
    POSITIVE LOGITS
    0
    0.56
     misure
    0.56
     opzioni
    0.55
    šech
    0.55
     regole
    0.52
     macchine
    0.52
     applicazioni
    0.51
     susun
    0.51
    ínguez
    0.50
     kristal
    0.49
    Activations Density 0.109%

    No Known Activations