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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4358
    Prev
    Next
    INDEX
    Explanations

    terms related to natural disasters and their impacts

    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
    +0.29
    1.1%
    1177
    +0.14
    0.6%
    394
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.29
    0.14
    964
    +0.14
    0.08
    1177
    +0.14
    0.00
    Negative Logits
    <bos>
    -2.39
    LayoutConstraint
    -0.90
    public
    -0.83
    .
    -0.83
    /*
    -0.81
    //
    -0.79
    〔
    -0.79
    TagMode
    -0.77
    ‏‏
    -0.75
    ComponentModel
    -0.75
    POSITIVE LOGITS
     affor
    2.69
     reluct
    2.67
     disagre
    2.65
     increa
    2.64
     emphat
    2.57
     maneu
    2.56
     impra
    2.53
     unwarran
    2.53
     inev
    2.51
     Juf
    2.48
    Activations Density 2.133%

    No Known Activations