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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 20817
    Prev
    Next
    INDEX
    Explanations

    words related to food and food-related activities or products

    oai_token-act-pair · gpt-3.5-turbo

    mentions of food and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Harley
    -0.73
     Wink
    -0.73
    owered
    -0.68
     Telegram
    -0.67
     Hardy
    -0.67
    itudinal
    -0.67
    20439
    -0.66
     Knight
    -0.65
     Caldwell
    -0.64
     Powers
    -0.64
    POSITIVE LOGITS
    stuff
    1.01
     eaten
    1.00
    food
    0.97
    borne
    0.96
    corn
    0.91
     tasted
    0.90
    cakes
    0.89
     starch
    0.89
     foods
    0.89
     meals
    0.88
    Activations Density 0.027%

    No Known Activations