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. 16131
    Prev
    Next
    INDEX
    Explanations

    references to different types of malt in beverages, particularly in the context of brewing beer

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to beer characteristics, particularly malt and hop 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
    vernment
    -0.83
     guiActiveUn
    -0.81
    LOS
    -0.78
    DragonMagazine
    -0.75
    pmwiki
    -0.74
    MpServer
    -0.69
     externalToEVAOnly
    -0.68
    Reply
    -0.67
     indemn
    -0.67
     Telecommunications
    -0.67
    POSITIVE LOGITS
     brewed
    1.05
     beers
    0.98
     blends
    0.97
     batches
    0.95
     bourbon
    0.95
     flavors
    0.94
     whiskey
    0.94
     tasting
    0.93
     flavor
    0.90
     flavored
    0.89
    Activations Density 0.147%

    No Known Activations