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. 222
    Prev
    Next
    INDEX
    Explanations

    phrases related to relief from medical conditions

    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
    468
    +0.09
    0.3%
    964
    +0.09
    0.3%
    876
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.09
    0.05
    736
    +0.09
    0.05
    1788
    +0.09
    0.03
    Negative Logits
     sappi
    -0.95
     Ottobre
    -0.94
     perche
    -0.91
     Luglio
    -0.91
     lancia
    -0.90
     partecipa
    -0.88
     parteci
    -0.85
     Giugno
    -0.84
     lusso
    -0.84
     costumi
    -0.83
    POSITIVE LOGITS
     symptoms
    0.85
     symptom
    0.75
     Symptoms
    0.68
     sufferer
    0.67
    Symptoms
    0.64
     pain
    0.63
     sufferers
    0.62
     discomfort
    0.60
     simpto
    0.58
     disagreeable
    0.58
    Activations Density 0.438%

    No Known Activations