© 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. 5064
    Prev
    Next
    INDEX
    Explanations

    descriptions of bodily functions or 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
    468
    +0.10
    0.3%
    1055
    +0.09
    0.2%
    624
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.10
    0.04
    946
    +0.09
    0.03
    468
    +0.08
    0.03
    Negative Logits
     !...
    -0.80
     ?...
    -0.76
     tene
    -0.72
     ‹
    -0.72
     Fasc
    -0.71
    :-(
    -0.71
     :*
    -0.70
     daz
    -0.70
     poichè
    -0.69
     perche
    -0.69
    POSITIVE LOGITS
    <bos>
    0.65
     pymysql
    0.64
     smtplib
    0.60
     urine
    0.60
     pymongo
    0.55
     spit
    0.55
     excreted
    0.54
     vomiting
    0.54
     coughed
    0.54
     spitting
    0.54
    Activations Density 0.179%

    No Known Activations