© 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. 7361
    Prev
    Next
    INDEX
    Explanations

    the word "repeat" and phrases around repetitive actions

    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
    674
    +0.08
    0.2%
    809
    +0.07
    0.2%
    1577
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1900
    +0.08
    0.02
    809
    +0.07
    0.03
    1666
    +0.07
    0.02
    Negative Logits
     doté
    -0.58
     renforcé
    -0.55
     proposée
    -0.52
     conçue
    -0.51
     proprement
    -0.50
    <bos>
    -0.49
     Junto
    -0.49
     Portugu
    -0.48
     conçus
    -0.48
    ándonos
    -0.47
    POSITIVE LOGITS
     repeat
    1.02
     Repeat
    0.91
    Repeat
    0.88
     repeating
    0.87
     repeats
    0.83
    repeat
    0.82
     repeated
    0.75
     rinse
    0.67
     repetition
    0.67
     repeti
    0.66
    Activations Density 0.287%

    No Known Activations