© 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. 3970
    Prev
    Next
    INDEX
    Explanations

    the term "caucus" in various contexts related to political processes

    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
    +0.14
    0.7%
    90
    +0.14
    0.7%
    506
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1492
    +0.14
    0.01
    506
    +0.14
    0.01
    313
    +0.14
    0.01
    Negative Logits
    <bos>
    -2.29
    <?
    -0.81
    //{
    -0.80
    <!--
    -0.70
    /**
    -0.68
    ////////
    -0.68
    AsUp
    -0.66
    hilt
    -0.66
    ///**
    -0.66
    /***
    -0.65
    POSITIVE LOGITS
     affor
    1.57
     unspeak
    1.55
     disagre
    1.55
     🤣🤣
    1.53
     impra
    1.53
     reluct
    1.51
     maneu
    1.51
     increa
    1.48
     excru
    1.45
     indescri
    1.44
    Activations Density 0.046%

    No Known Activations