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. 15852
    Prev
    Next
    INDEX
    Explanations

    keywords related to the company "Netflix," including names of co-founders, mentions of company information, and references to Netflix productions

    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
    1757
    +0.16
    0.6%
    1328
    +0.15
    0.6%
    1351
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1351
    +0.16
    0.02
    1757
    +0.15
    0.02
    1328
    +0.14
    0.02
    Negative Logits
    asteroide
    -0.61
    relenting
    -0.58
    DataPropertyName
    -0.58
    mistak
    -0.58
    wavering
    -0.57
     voyons
    -0.57
     constate
    -0.56
     viendra
    -0.55
     zů
    -0.55
    sightly
    -0.54
    POSITIVE LOGITS
    Netflix
    1.30
     Netflix
    1.29
     netflix
    1.03
    netflix
    0.92
     OTT
    0.51
     streaming
    0.45
     membership
    0.44
     Streaming
    0.44
     Ryan
    0.44
     Burbank
    0.44
    Activations Density 0.079%

    No Known Activations