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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15320
    Prev
    Next
    INDEX
    Explanations

    direct quotes starting with the word "Don"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1604
    +0.13
    0.5%
    1335
    +0.13
    0.5%
    812
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1604
    +0.13
    0.04
    1335
    +0.13
    0.05
    812
    +0.11
    0.03
    Negative Logits
     saites
    -0.49
    HasForeignKey
    -0.49
    ibatis
    -0.49
    reactivex
    -0.47
    chartInstance
    -0.46
    囗
    -0.46
    clable
    -0.42
     розта
    -0.42
    Население
    -0.42
     виді
    -0.42
    POSITIVE LOGITS
     désol
    0.98
     disagre
    0.92
     DON
    0.91
     effray
    0.91
    Don
    0.89
     malheure
    0.88
     Don
    0.86
     encomp
    0.85
     osal
    0.85
     unwarran
    0.84
    Activations Density 0.091%

    No Known Activations