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. 16018
    Prev
    Next
    INDEX
    Explanations

    categories or sections in a document

    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
    1343
    +0.12
    0.3%
    453
    +0.09
    0.3%
    325
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2002
    +0.12
    0.03
    450
    +0.09
    0.03
    189
    +0.08
    0.02
    Negative Logits
     Kø
    -0.51
     vagu
    -0.46
     toon
    -0.45
     Boulogne
    -0.45
     Pyrénées
    -0.43
     Languedoc
    -0.42
     cession
    -0.42
     Yeni
    -0.42
     År
    -0.41
     Dord
    -0.41
    POSITIVE LOGITS
     javier
    0.74
     felipe
    0.72
     alberto
    0.70
     rafael
    0.69
     fernando
    0.66
     sergio
    0.65
     jorge
    0.63
    PerformLayout
    0.63
     cristina
    0.62
     eduardo
    0.59
    Activations Density 0.048%

    No Known Activations