© 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. 11196
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal complaints or formal academic studies

    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
    1870
    +0.16
    0.6%
    90
    +0.14
    0.5%
    1407
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1407
    +0.16
    0.02
    90
    +0.14
    0.02
    1077
    +0.13
    0.02
    Negative Logits
     Ause
    -0.50
    ellemző
    -0.49
     Zuh
    -0.49
     fii
    -0.48
    astricht
    -0.47
     chanti
    -0.47
     gilet
    -0.47
     broderie
    -0.47
    avyzd
    -0.46
     pét
    -0.46
    POSITIVE LOGITS
    Formal
    1.16
     formal
    1.14
     Formal
    1.11
    formal
    1.05
     formalized
    0.91
     formales
    0.86
     formally
    0.82
     formality
    0.81
     informal
    0.81
     Informal
    0.80
    Activations Density 0.060%

    No Known Activations