© 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. 3-RES-JB
    11. 23131
    Prev
    Next
    INDEX
    Explanations

    phrases related to serving or presenting food

    oai_token-act-pair · gpt-3.5-turbo

    the word "serve" and its variations, indicating content related to serving food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orsi
    -0.73
    phas
    -0.70
    braska
    -0.68
    razil
    -0.68
    ilateral
    -0.67
    lex
    -0.66
    orne
    -0.65
    peria
    -0.64
    requisite
    -0.64
    ortex
    -0.63
    POSITIVE LOGITS
     meals
    0.97
     Serving
    0.90
     Delicious
    0.86
     servings
    0.86
     SERV
    0.85
     Meal
    0.84
     Restaur
    0.83
    Serv
    0.83
     kitchens
    0.83
    ings
    0.79
    Activations Density 0.017%

    No Known Activations