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. 15952
    Prev
    Next
    INDEX
    Explanations

    descriptions related to flavors and aromas, especially those associated with drinks

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of flavor profiles and aromas

    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
     Contracts
    -0.91
     Canaver
    -0.85
    Account
    -0.80
     License
    -0.79
     Volunteer
    -0.78
    Dispatch
    -0.77
    imens
    -0.77
    Fax
    -0.75
    quest
    -0.74
    ticket
    -0.72
    POSITIVE LOGITS
     texture
    1.33
     sweetness
    1.29
     creamy
    1.24
     shimmer
    1.21
     fragrance
    1.12
     aroma
    1.09
     textures
    1.09
     layered
    1.07
     arom
    1.04
     flavorful
    1.03
    Activations Density 0.319%

    No Known Activations