© 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. 2247
    Prev
    Next
    INDEX
    Explanations

    words related to customer service and support

    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
    946
    +0.14
    0.4%
    1403
    +0.13
    0.4%
    1150
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.14
    0.05
    1403
    +0.13
    0.01
    1553
    +0.10
    0.04
    Negative Logits
     Seigneur
    -0.77
     Abbé
    -0.71
     Messieurs
    -0.70
     Docteur
    -0.70
     oiseau
    -0.68
     giovanni
    -0.64
     curé
    -0.64
     volunte
    -0.62
     alberto
    -0.62
     Mlle
    -0.62
    POSITIVE LOGITS
     assistance
    0.69
     helpline
    0.69
     hotline
    0.64
     Assistance
    0.64
     contact
    0.62
    assistance
    0.61
     customer
    0.57
     questions
    0.57
    bleshooting
    0.56
     concierge
    0.56
    Activations Density 0.349%

    No Known Activations