© 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 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. 14131
    Prev
    Next
    INDEX
    Explanations

    words related to political leaders and international relations, specifically focusing on African political figures

    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
    629
    +0.14
    0.6%
    228
    +0.13
    0.6%
    1416
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.14
    0.07
    629
    +0.13
    0.04
    395
    +0.13
    0.06
    Negative Logits
     iesp
    -0.78
     šķ
    -0.78
     ģ
    -0.77
     vēl
    -0.77
     ķ
    -0.76
     ļ
    -0.75
     īpa
    -0.69
     liel
    -0.68
     jeb
    -0.67
     ieg
    -0.67
    POSITIVE LOGITS
     coar
    1.21
     unwarran
    1.18
     depic
    1.18
     snoopy
    1.16
     inev
    1.15
     increa
    1.13
     hentai
    1.10
     madonna
    1.10
     shenan
    1.10
     berea
    1.10
    Activations Density 0.400%

    No Known Activations