Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 22224
    Prev
    Next
    INDEX
    Explanations

    food-related terms, specifically related to flavors

    oai_token-act-pair · gpt-3.5-turbo

    references to flavor and aroma, particularly in the context of food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rams
    -0.68
     Lak
    -0.67
     Lions
    -0.65
    shire
    -0.65
     Nikon
    -0.64
     Telecommunications
    -0.63
    pload
    -0.60
     Commissioners
    -0.60
     Citizen
    -0.60
    upon
    -0.60
    POSITIVE LOGITS
     buds
    1.03
     juices
    1.03
     flavor
    1.02
     palate
    0.96
     flavored
    0.95
    bite
    0.89
     flavour
    0.88
     Flav
    0.88
     enh
    0.87
     Flavoring
    0.86
    Activations Density 0.039%

    No Known Activations