© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 7851
    Prev
    Next
    INDEX
    Explanations

    phrases related to food and food insecurity

    oai_token-act-pair · gpt-3.5-turbo

    statistical information about food insecurity and its impact on families

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spectre
    -1.00
     Quinn
    -0.87
     Arkham
    -0.84
     Weld
    -0.79
    ãĤ´
    -0.78
     Mehran
    -0.77
     Aur
    -0.76
    brush
    -0.76
     Reeves
    -0.75
     Valkyrie
    -0.75
    POSITIVE LOGITS
     food
    2.16
    Food
    2.12
     foods
    2.06
     meal
    2.05
    food
    2.04
     meals
    2.03
     Food
    2.02
     culinary
    2.01
     eating
    1.96
     chefs
    1.90
    Activations Density 0.741%

    No Known Activations