© 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. 14729
    Prev
    Next
    INDEX
    Explanations

    phrases related to conspiracy theories and extremist ideologies

    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
    1741
    +0.27
    1.0%
    50
    +0.23
    0.8%
    2019
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.27
    0.08
    50
    +0.23
    0.06
    1287
    +0.16
    0.04
    Negative Logits
     shouldBe
    -0.62
     įsi
    -0.59
     rayures
    -0.57
     apsau
    -0.54
     gardien
    -0.52
     attaques
    -0.51
     nė
    -0.51
     spreken
    -0.51
     naudoti
    -0.51
     virš
    -0.51
    POSITIVE LOGITS
     magis
    0.84
     tamen
    0.77
     palab
    0.75
    Läh
    0.74
    Mitä
    0.74
     mef
    0.73
     ibi
    0.71
     reputa
    0.70
    Sklici
    0.70
     priva
    0.69
    Activations Density 0.345%

    No Known Activations