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. 1379
    Prev
    Next
    INDEX
    Explanations

    situations related to sponsorships and contracts

    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
    1403
    +0.11
    0.3%
    678
    +0.10
    0.3%
    227
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1360
    +0.11
    0.03
    429
    +0.10
    0.03
    1490
    +0.10
    0.04
    Negative Logits
    ghijkl
    -0.60
    ModelMap
    -0.60
    ==="
    -0.58
     onCancelled
    -0.56
    uchtigkeit
    -0.56
    hObject
    -0.54
    JTextArea
    -0.53
    ItemBackground
    -0.53
    IsUnicode
    -0.52
    <>());
    -0.52
    POSITIVE LOGITS
     Sponsorship
    0.81
     partnership
    0.81
     shenan
    0.78
     sponsorship
    0.78
    partnership
    0.77
     Agreed
    0.76
     uniqu
    0.75
     Incenti
    0.74
     Chronology
    0.74
     Confu
    0.73
    Activations Density 0.348%

    No Known Activations