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. 1664
    Prev
    Next
    INDEX
    Explanations

    references to motion or movement, such as cameras, sensors, or physical actions

    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
    680
    +0.16
    0.7%
    1870
    +0.16
    0.7%
    1053
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.16
    0.02
    1805
    +0.16
    0.01
    201
    +0.12
    0.01
    Negative Logits
    GraphicsUnit
    -0.48
    شهاد
    -0.45
     iniqu
    -0.44
    Cambridge
    -0.42
     Cambridge
    -0.41
    柿
    -0.41
    猾
    -0.40
    Jub
    -0.40
     незавершена
    -0.40
    Lus
    -0.40
    POSITIVE LOGITS
     motion
    1.26
    motion
    1.15
     Motion
    1.14
     MOTION
    1.10
     motions
    1.10
    Motion
    1.06
     Motions
    0.92
    MOTION
    0.86
    motions
    0.85
     uncin
    0.70
    Activations Density 0.082%

    No Known Activations