© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 5047
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate legal disclaimers and lack of sponsorship

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.26
    0.9%
    438
    +0.10
    0.3%
    878
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.26
    0.07
    208
    +0.10
    0.06
    878
    +0.08
    0.06
    Negative Logits
    <bos>
    -1.97
    ColumnHeaders
    -0.61
    bzero
    -0.56
     onStop
    -0.54
    ostringstream
    -0.52
    GeneratedCode
    -0.52
    AlterField
    -0.52
    displayquote
    -0.51
    <!--
    -0.51
     AssemblyCompany
    -0.51
    POSITIVE LOGITS
     venuto
    1.10
     cammin
    1.00
     affez
    0.95
     soggior
    0.95
     Settembre
    0.94
     bandung
    0.94
     fuo
    0.89
     silikon
    0.88
     Muhamma
    0.88
     torba
    0.87
    Activations Density 0.497%

    No Known Activations