© 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. 15152
    Prev
    Next
    INDEX
    Explanations

    expressions of physical affection, particularly hugging

    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
    1823
    +0.10
    0.3%
    1899
    +0.09
    0.2%
    1533
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1823
    +0.10
    0.03
    509
    +0.09
    0.04
    736
    +0.09
    0.04
    Negative Logits
     kesi
    -0.61
     jaya
    -0.60
     saha
    -0.60
     istan
    -0.58
     maksi
    -0.56
     vider
    -0.56
     felipe
    -0.56
     rodrigo
    -0.54
     alberto
    -0.54
     kasa
    -0.54
    POSITIVE LOGITS
     hug
    0.66
    <bos>
    0.63
     hugged
    0.62
     hugs
    0.61
     hugging
    0.57
    queeze
    0.55
     comforting
    0.55
    hug
    0.52
     embrace
    0.51
    Hug
    0.50
    Activations Density 0.193%

    No Known Activations