© 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. 777
    Prev
    Next
    INDEX
    Explanations

    terms related to business layoffs and job cuts

    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
    509
    +0.10
    0.3%
    1385
    +0.09
    0.3%
    1445
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.10
    0.02
    1939
    +0.09
    0.02
    954
    +0.08
    0.03
    Negative Logits
     bâton
    -0.64
     jacques
    -0.61
     propriétaires
    -0.60
     nicolas
    -0.58
     chapeau
    -0.56
     balenciaga
    -0.55
     moulin
    -0.55
     ɛ
    -0.55
     fauteuil
    -0.54
     abbiano
    -0.54
    POSITIVE LOGITS
     staff
    0.96
     employees
    0.95
     workforce
    0.86
     staffers
    0.80
     staffing
    0.79
    staff
    0.77
     Staff
    0.76
     employee
    0.75
     Employees
    0.75
     staffs
    0.73
    Activations Density 0.435%

    No Known Activations