© 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 EvalsExportsAPI 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. 6010
    Prev
    Next
    INDEX
    Explanations

    commands related to compiling and execution of code

    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
    168
    +0.19
    0.7%
    410
    +0.17
    0.7%
    1325
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.19
    0.02
    410
    +0.17
    0.02
    976
    +0.12
    0.02
    Negative Logits
     fup
    -1.02
     fta
    -0.99
     desir
    -0.97
     perfon
    -0.96
     ACKNOWLEDGMENTS
    -0.95
     ftu
    -0.95
     effe
    -0.94
     embra
    -0.94
     »>
    -0.92
     fte
    -0.91
    POSITIVE LOGITS
     compile
    1.26
    compile
    1.20
     compiled
    1.15
     compilation
    1.13
     compiling
    1.08
    compiled
    1.06
     compiler
    1.04
    Compile
    1.01
     compiles
    0.98
    compilation
    0.93
    Activations Density 0.088%

    No Known Activations