© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1645
    Prev
    Next
    INDEX
    Explanations

    phrases related to questions and answers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.24
    0.9%
    872
    +0.10
    0.4%
    1639
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.24
    0.05
    1314
    +0.10
    0.04
    781
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.41
    Autoritní
    -0.52
    GIVEREF
    -0.52
    FunctionFlags
    -0.50
    <?
    
    -0.48
    usercontent
    -0.48
     ddelweddau
    -0.47
    Према
    -0.47
     socialize
    -0.46
    arrange
    -0.46
    POSITIVE LOGITS
     questions
    1.18
     question
    1.16
     pylab
    0.98
    questions
    0.98
     unanswered
    0.97
     viciss
    0.97
     pymysql
    0.97
     smtplib
    0.97
     Questions
    0.96
     kysy
    0.93
    Activations Density 0.303%

    No Known Activations