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. 713
    Prev
    Next
    INDEX
    Explanations

    job titles and roles in employment contexts

    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
    +0.32
    1.2%
    1013
    +0.14
    0.5%
    227
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.32
    0.07
    1013
    +0.14
    0.07
    1980
    +0.14
    0.04
    Negative Logits
    <bos>
    -1.53
    //---
    -0.56
     lengthen
    -0.56
    //<
    -0.55
    //...
    -0.55
    ૌ
    -0.54
     contend
    -0.54
     transcend
    -0.50
    //--
    -0.50
    ⇔
    -0.49
    POSITIVE LOGITS
     Juf
    0.96
     zove
    0.96
     Bekasi
    0.96
     Palembang
    0.96
     rafra
    0.93
     swarovski
    0.92
     Minang
    0.91
     montagna
    0.91
     Italij
    0.89
     ducato
    0.88
    Activations Density 0.552%

    No Known Activations