© 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. 0-RES-JB
    11. 4984
    Prev
    Next
    INDEX
    Explanations

    phrases related to a kitchen setting

    oai_token-act-pair · gpt-3.5-turbo

    references to kitchens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Colossus
    -0.74
     Offline
    -0.72
    ases
    -0.71
     Figures
    -0.70
    OPA
    -0.68
    hips
    -0.68
     Torrent
    -0.67
    nesty
    -0.66
    uff
    -0.66
    TPP
    -0.65
    POSITIVE LOGITS
     kitchen
    3.43
     kitchens
    2.81
     Kitchen
    2.11
     cook
    1.73
     culinary
    1.69
     fridge
    1.68
     cooks
    1.68
     cooking
    1.60
     chef
    1.59
     bathroom
    1.59
    Activations Density 0.013%

    No Known Activations