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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 20079
    Prev
    Next
    INDEX
    Explanations

    references to flavors, aromas, and ingredients in food

    oai_token-act-pair · gpt-3.5-turbo

    references to flavor and aroma in food descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rams
    -0.68
    chy
    -0.68
    shire
    -0.68
     Commissioners
    -0.66
     Aerospace
    -0.63
     Lions
    -0.63
     Lak
    -0.63
     Telecommunications
    -0.63
     Osw
    -0.62
     Contracts
    -0.61
    POSITIVE LOGITS
     flavor
    0.99
     buds
    0.98
     juices
    0.96
     flavored
    0.93
     palate
    0.89
     flavour
    0.88
     Flav
    0.84
     flavors
    0.84
    bite
    0.83
    fruit
    0.80
    Activations Density 0.019%

    No Known Activations