© 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. 9507
    Prev
    Next
    INDEX
    Explanations

    descriptions related to various tastes and flavors

    oai_token-act-pair · gpt-3.5-turbo

    references to taste and flavor in relation to food experiences

    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
     Lak
    -0.74
    chy
    -0.72
     disbanded
    -0.65
     Creed
    -0.64
     Freeman
    -0.63
    knit
    -0.63
     Sto
    -0.62
     CST
    -0.61
    kson
    -0.60
    asketball
    -0.60
    POSITIVE LOGITS
     buds
    1.56
     palate
    1.10
     tasting
    0.96
     enh
    0.95
     sensations
    0.92
     testers
    0.92
    ubi
    0.90
     Flavoring
    0.88
    terness
    0.86
     tastes
    0.86
    Activations Density 0.068%

    No Known Activations