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. 15409
    Prev
    Next
    INDEX
    Explanations

    structured elements within text data, especially related to API routes and commands in a technical context

    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
    1842
    +0.13
    0.4%
    1978
    +0.13
    0.4%
    876
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.13
    -0.00
    678
    +0.13
    0.03
    631
    +0.12
    0.01
    Negative Logits
     hoody
    -0.83
     Magdal
    -0.75
     Mahomet
    -0.75
     Punj
    -0.73
     Momb
    -0.65
     reconno
    -0.63
     Bagdad
    -0.62
     Lieut
    -0.61
     indestru
    -0.61
     Khart
    -0.60
    POSITIVE LOGITS
    some
    0.54
     succede
    0.54
    zembro
    0.51
     Parce
    0.50
    complish
    0.49
    nother
    0.48
    stuff
    0.48
     visst
    0.48
    iální
    0.47
     varian
    0.47
    Activations Density 0.182%

    No Known Activations