© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2106
    Prev
    Next
    INDEX
    Explanations

    information related to workplace safety, accidents, and risks

    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
    658
    +0.11
    0.3%
    1600
    +0.09
    0.3%
    100
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.11
    0.07
    100
    +0.09
    0.04
    1600
    +0.09
    0.05
    Negative Logits
     Gallimard
    -0.62
     parlar
    -0.61
     Ressource
    -0.57
    rozco
    -0.57
     Verk
    -0.56
    gorov
    -0.55
     veu
    -0.55
     CreateTagHelper
    -0.55
     Portail
    -0.52
     kado
    -0.52
    POSITIVE LOGITS
     safety
    0.93
     accidents
    0.87
     Accidents
    0.83
     accident
    0.79
    safety
    0.78
     unsafe
    0.76
     Safety
    0.76
     safer
    0.74
     fatalities
    0.73
    unsafe
    0.73
    Activations Density 0.695%

    No Known Activations