© 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. 6313
    Prev
    Next
    INDEX
    Explanations

    phrases related to beliefs or opinions

    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
    1950
    +0.10
    0.3%
    878
    +0.09
    0.3%
    547
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1950
    +0.10
    0.06
    971
    +0.09
    0.04
    878
    +0.09
    0.05
    Negative Logits
     saurait
    -0.65
     trouvait
    -0.57
     occupe
    -0.54
    vgili
    -0.54
    Çok
    -0.52
     Normalmente
    -0.52
     accueille
    -0.52
    ginald
    -0.51
    maksud
    -0.49
    Szia
    -0.49
    POSITIVE LOGITS
     purtroppo
    0.61
     BELIEVE
    0.60
     believe
    0.58
     😭😭
    0.57
     boop
    0.56
     rascal
    0.56
     crede
    0.56
     motherfucker
    0.56
     polypep
    0.55
     shenan
    0.55
    Activations Density 0.192%

    No Known Activations