Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8433
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "wage" and related terms, as well as discussions related to wages, labor, and economic systems

    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
    67
    +0.12
    0.4%
    1350
    +0.12
    0.4%
    1870
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.12
    0.03
    67
    +0.12
    0.02
    783
    +0.12
    0.02
    Negative Logits
     embra
    -0.90
     effe
    -0.84
     dispen
    -0.83
     accla
    -0.81
     trit
    -0.81
     adh
    -0.81
     pessi
    -0.80
     desir
    -0.80
     fup
    -0.80
     fuf
    -0.78
    POSITIVE LOGITS
     wage
    1.28
     wages
    1.17
    wage
    1.07
     Wage
    1.06
    Wage
    0.97
     Wages
    0.91
     salary
    0.86
     salaries
    0.72
     pay
    0.70
     payroll
    0.67
    Activations Density 0.081%

    No Known Activations