© 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 EvalsExportsinterp-engineNEWAPI 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. 14930
    Prev
    Next
    INDEX
    Explanations

    information related to traffic rules and regulations

    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
    453
    +0.14
    0.4%
    2019
    +0.13
    0.4%
    1438
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    305
    +0.14
    0.02
    191
    +0.13
    0.02
    974
    +0.10
    0.02
    Negative Logits
     motherfucker
    -0.70
     bougie
    -0.66
    nasel
    -0.63
     caucasian
    -0.63
     spartan
    -0.63
    wurde
    -0.61
     hobo
    -0.59
     duffel
    -0.59
     xPos
    -0.59
     mercurial
    -0.59
    POSITIVE LOGITS
     kafe
    1.03
     silikon
    1.00
     keramik
    0.93
     panik
    0.93
     optik
    0.90
     antik
    0.88
     maksi
    0.87
     seksi
    0.86
     konsult
    0.85
     kosme
    0.84
    Activations Density 0.044%

    No Known Activations