© 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. 6728
    Prev
    Next
    INDEX
    Explanations

    mentions of labor-related terms, labor conditions, and labor market activities

    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
    1331
    +0.16
    0.6%
    680
    +0.16
    0.6%
    1870
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1331
    +0.16
    0.04
    517
    +0.16
    0.03
    303
    +0.15
    0.04
    Negative Logits
     personalise
    -0.51
     gratify
    -0.50
     chaste
    -0.47
     purify
    -0.47
     poetical
    -0.45
     mortgagee
    -0.44
     entitle
    -0.44
     solidify
    -0.44
     distort
    -0.44
     optimise
    -0.44
    POSITIVE LOGITS
     labor
    1.24
     Labor
    1.17
    Labor
    1.16
    labor
    1.13
     labour
    1.13
    Labour
    1.10
     Labour
    1.10
     LABOR
    1.09
    labour
    1.02
    LABOR
    0.83
    Activations Density 0.062%

    No Known Activations