© 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. 5093
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional intelligence and self-awareness

    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
    604
    +0.09
    0.2%
    1609
    +0.07
    0.2%
    855
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.09
    0.03
    610
    +0.07
    0.04
    96
    +0.07
    0.01
    Negative Logits
     utop
    -1.08
     ordina
    -1.04
     kram
    -1.04
     lele
    -1.04
     meis
    -1.02
     ananas
    -1.02
     grati
    -0.99
     maroc
    -0.97
     gmbh
    -0.97
     solidar
    -0.97
    POSITIVE LOGITS
     unable
    0.86
     cannot
    0.80
     inability
    0.79
     therefore
    0.77
     unaware
    0.73
     couldn
    0.71
     lack
    0.69
     lacks
    0.67
    cannot
    0.67
    unable
    0.65
    Activations Density 0.504%

    No Known Activations