© 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. 5024
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lay" and its variations in different contexts

    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
    +0.21
    1.1%
    1837
    +0.14
    0.7%
    228
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1837
    +0.21
    0.03
    1472
    +0.14
    0.02
    228
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.49
    PreAuthorize
    -0.74
    IActionResult
    -0.69
    maxcdn
    -0.69
    CodeDom
    -0.65
    HasOne
    -0.64
    JspWriter
    -0.64
    MockBean
    -0.64
    Unmarshaller
    -0.63
    pod
    -0.63
    POSITIVE LOGITS
     shenan
    1.75
     maneu
    1.74
     emphat
    1.71
     milf
    1.69
     impra
    1.67
     indestru
    1.65
     affor
    1.64
     disreg
    1.62
     resear
    1.59
     snoopy
    1.58
    Activations Density 0.042%

    No Known Activations