© 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. 16352
    Prev
    Next
    INDEX
    Explanations

    mentions of types of weightlifting exercises, specifically focusing on exercises related to bench pressing

    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
    1145
    +0.18
    0.7%
    1328
    +0.16
    0.7%
    1350
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1145
    +0.18
    0.02
    1328
    +0.16
    0.02
    1604
    +0.13
    0.01
    Negative Logits
     gild
    -0.80
     strick
    -0.77
     affor
    -0.75
     encomp
    -0.75
     greate
    -0.74
     emphat
    -0.72
     perfet
    -0.71
     alre
    -0.70
     Godt
    -0.69
     madonna
    -0.69
    POSITIVE LOGITS
     bench
    1.55
     Bench
    1.43
    bench
    1.43
    Bench
    1.28
     benches
    1.27
    BENCH
    1.17
     benchmark
    1.05
     benchmarks
    0.97
     Benchmark
    0.93
    benchmark
    0.91
    Activations Density 0.072%

    No Known Activations