© 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. 14884
    Prev
    Next
    INDEX
    Explanations

    words related to politics, government, and specific 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
    544
    +0.14
    0.5%
    1296
    +0.13
    0.5%
    479
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1296
    +0.14
    0.05
    544
    +0.13
    0.04
    1994
    +0.13
    0.04
    Negative Logits
     swarovski
    -1.06
     ecru
    -1.05
     hairc
    -1.00
     suscep
    -0.93
     unlaw
    -0.92
     bandeau
    -0.92
     reluct
    -0.88
     velour
    -0.88
     pyjama
    -0.87
     ingrat
    -0.86
    POSITIVE LOGITS
     Clinton
    1.62
    Clinton
    1.48
    CLIN
    0.97
     Clint
    0.93
     CLIN
    0.88
    Clint
    0.82
     Hillary
    0.81
    Hillary
    0.80
    cl
    0.79
     cl
    0.78
    Activations Density 0.054%

    No Known Activations