Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 6783
    Prev
    Next
    INDEX
    Explanations

    cooking processes and techniques, especially involving mixing and combining ingredients

    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
    +0.25
    1.0%
    876
    +0.12
    0.5%
    1150
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.25
    0.03
    1284
    +0.12
    0.03
    736
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.30
    /***
    
    -0.84
    ///**
    -0.67
    CreateIndex
    -0.64
    //});
    -0.63
    tinyos
    -0.62
     assistir
    -0.62
    <tfoot>
    -0.62
    PageContext
    -0.62
    rungsseite
    -0.60
    POSITIVE LOGITS
     lidl
    1.04
     curieux
    1.01
     chrysler
    1.00
     pymysql
    0.99
     eiffel
    0.98
     tucson
    0.97
     lamborghini
    0.95
     hilton
    0.95
     malheureux
    0.94
     affor
    0.94
    Activations Density 0.082%

    No Known Activations