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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13466
    Prev
    Next
    INDEX
    Explanations

    words related to labor and employment issues, particularly around wages and conflicts in the workplace

    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
    31
    +0.14
    0.6%
    812
    +0.13
    0.5%
    1194
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1194
    +0.14
    0.03
    1233
    +0.13
    0.03
    812
    +0.12
    0.02
    Negative Logits
     prič
    -0.66
    Może
    -0.64
    Další
    -0.56
    Díky
    -0.55
    Zdroj
    -0.55
    Více
    -0.53
    Sklici
    -0.53
    Zgod
    -0.53
    Výhody
    -0.51
    Dzięki
    -0.51
    POSITIVE LOGITS
     Po
    1.20
    Po
    1.19
     po
    1.10
     polig
    1.02
    po
    0.98
     PO
    0.98
     popo
    0.93
     pob
    0.91
     Pola
    0.86
     alberto
    0.85
    Activations Density 0.112%

    No Known Activations