© 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. 11327
    Prev
    Next
    INDEX
    Explanations

    various words related to awareness, consciousness, and mental states

    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
    2015
    +0.17
    0.5%
    509
    +0.15
    0.4%
    1446
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.17
    0.08
    1446
    +0.15
    0.04
    2015
    +0.12
    0.00
    Negative Logits
     praktik
    -0.69
     Kese
    -0.68
     Demokrat
    -0.67
     Pende
    -0.65
     akut
    -0.64
     minimalis
    -0.63
     pessi
    -0.61
     intimid
    -0.60
     kosme
    -0.60
     kön
    -0.59
    POSITIVE LOGITS
    <bos>
    1.11
    assertIn
    0.60
    Choisissez
    0.58
     compagnon
    0.57
     (*(
    0.56
     dæ
    0.55
     créateur
    0.54
    Vlastnosti
    0.54
    Dziękuję
    0.53
    RemoveField
    0.53
    Activations Density 0.737%

    No Known Activations