© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 15208
    Prev
    Next
    INDEX
    Explanations

    verbs related to starting or beginning

    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
    1392
    +0.12
    0.4%
    1937
    +0.10
    0.3%
    1425
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1392
    +0.12
    0.06
    1381
    +0.10
    0.05
    120
    +0.10
    0.04
    Negative Logits
     peppa
    -0.60
     komende
    -0.59
     pooh
    -0.58
     shenan
    -0.57
     Tweede
    -0.56
     ineffec
    -0.55
     milf
    -0.54
     vierge
    -0.53
     déchir
    -0.52
     bahia
    -0.51
    POSITIVE LOGITS
     started
    0.77
    started
    0.72
     STARTED
    0.68
     start
    0.66
    Started
    0.63
    STARTED
    0.63
     began
    0.63
     START
    0.61
     starts
    0.61
     Started
    0.60
    Activations Density 0.108%

    No Known Activations