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. 451
    Prev
    Next
    INDEX
    Explanations

    phrases related to drones and aerial videography

    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
    251
    +0.17
    0.6%
    1870
    +0.13
    0.5%
    805
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.17
    0.02
    805
    +0.13
    0.02
    1515
    +0.12
    0.01
    Negative Logits
     كومونز
    -0.67
     censiti
    -0.64
    PerformLayout
    -0.63
    GraphicsUnit
    -0.54
     Pata
    -0.51
     Gord
    -0.51
     autorytatywna
    -0.50
    testify
    -0.49
     Sauber
    -0.49
     MainAxisSize
    -0.49
    POSITIVE LOGITS
     drone
    1.19
     drones
    1.16
    drone
    1.03
    Drone
    0.94
     Drone
    0.90
     Drones
    0.83
     dron
    0.66
     UAV
    0.62
     barbacoa
    0.61
    rones
    0.61
    Activations Density 0.084%

    No Known Activations