© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1979
    Prev
    Next
    INDEX
    Explanations

    mentions of diapers and related products

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    511
    +0.09
    0.3%
    1047
    +0.08
    0.2%
    1044
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.09
    0.04
    368
    +0.08
    0.03
    1137
    +0.07
    0.04
    Negative Logits
    ofield
    -0.66
     mList
    -0.59
     vedno
    -0.58
     maksi
    -0.57
     contex
    -0.57
     veliko
    -0.56
     Böh
    -0.56
     šte
    -0.56
     bolj
    -0.55
     resul
    -0.54
    POSITIVE LOGITS
     diaper
    2.08
     diapers
    2.00
     napp
    1.30
     nursery
    1.25
     potty
    1.23
     stroller
    1.23
     toddlers
    1.22
     preschool
    1.19
     toddler
    1.18
     daycare
    1.13
    Activations Density 0.273%

    No Known Activations