© 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. 10776
    Prev
    Next
    INDEX
    Explanations

    references to political opposition and conflict

    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
    1325
    +0.16
    0.6%
    1810
    +0.13
    0.5%
    1778
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1325
    +0.16
    0.03
    1778
    +0.13
    0.03
    321
    +0.13
    0.04
    Negative Logits
    Cari
    -0.55
     Cari
    -0.53
    asteroide
    -0.48
     attirer
    -0.47
     diffusi
    -0.47
     actualité
    -0.46
     amitié
    -0.46
     cari
    -0.45
     PHILOS
    -0.45
    Enumer
    -0.45
    POSITIVE LOGITS
     opposition
    1.17
     Opposition
    1.02
    Opposition
    1.01
    opposition
    0.98
     opposed
    0.98
     oppose
    0.95
     opposing
    0.95
     opponent
    0.94
     opposes
    0.93
     opponents
    0.92
    Activations Density 0.081%

    No Known Activations