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. 1014
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "Ex" in various forms

    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
    783
    +0.16
    0.9%
    50
    +0.15
    0.8%
    1604
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.16
    0.03
    1604
    +0.15
    0.03
    597
    +0.14
    0.02
    Negative Logits
    <bos>
    -2.45
    Autoritní
    -0.70
     autorytatywna
    -0.68
    typeorm
    -0.67
    ⓧ
    -0.67
    ViewFeatures
    -0.66
    Comun
    -0.63
    França
    -0.63
    glPushMatrix
    -0.62
    Mó
    -0.62
    POSITIVE LOGITS
     kyo
    1.29
     santiago
    1.24
     exciter
    1.22
     exem
    1.19
     jaya
    1.17
     stockholm
    1.15
     maroc
    1.15
     accla
    1.15
     contex
    1.15
     parch
    1.15
    Activations Density 0.078%

    No Known Activations