© 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. 4-RES-JB
    11. 7230
    Prev
    Next
    INDEX
    Explanations

    food-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to food

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

    No Comments

    Negative Logits
    20439
    -0.82
     Wink
    -0.78
    itudinal
    -0.74
     Powers
    -0.72
     Telegram
    -0.71
     Archangel
    -0.68
    aird
    -0.68
     2022
    -0.68
     Crosby
    -0.68
     Gib
    -0.67
    POSITIVE LOGITS
    stuff
    1.09
    borne
    0.95
     eaten
    0.91
     eater
    0.91
     tasted
    0.91
    cakes
    0.88
    meat
    0.87
     poisoning
    0.87
    namese
    0.86
     additives
    0.86
    Activations Density 0.022%

    No Known Activations