© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1894
    Prev
    Next
    INDEX
    Explanations

    phrases related to inefficiency and wastefulness

    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
    1482
    +0.15
    0.5%
    1272
    +0.14
    0.5%
    11
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.15
    0.03
    1272
    +0.14
    0.02
    1482
    +0.13
    0.02
    Negative Logits
     Momb
    -0.70
     Rodrig
    -0.68
     belliger
    -0.67
    XmlEnum
    -0.64
     Herv
    -0.61
     Vaugh
    -0.59
     Frankfort
    -0.58
     Nare
    -0.57
     Reng
    -0.57
     Dov
    -0.57
    POSITIVE LOGITS
     waste
    1.42
    waste
    1.33
    Waste
    1.30
     Waste
    1.28
     WASTE
    1.19
     wastes
    1.13
    WASTE
    1.07
     wasted
    0.99
     wasting
    0.93
     Wastes
    0.90
    Activations Density 0.072%

    No Known Activations