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

    Neuronpedia

    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. 6784
    Prev
    Next
    INDEX
    Explanations

    information related to workout routines and weightlifting exercises

    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
    876
    +0.12
    0.3%
    1553
    +0.10
    0.3%
    736
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.12
    0.04
    37
    +0.10
    0.02
    1877
    +0.09
    0.03
    Negative Logits
     ecclesias
    -0.98
     monaster
    -0.96
     alkoh
    -0.88
     ivi
    -0.88
     socie
    -0.87
     vian
    -0.86
     Ibidem
    -0.84
     magis
    -0.83
     Cfr
    -0.83
     ria
    -0.81
    POSITIVE LOGITS
     repetitions
    0.58
     workouts
    0.57
     workout
    0.56
     reps
    0.54
     repetition
    0.54
     load
    0.52
     exercises
    0.51
     exercise
    0.51
     technique
    0.50
     variation
    0.50
    Activations Density 0.209%

    No Known Activations