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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 15
    Prev
    Next
    INDEX
    Explanations

    details related to consuming beverages

    oai_token-act-pair · gpt-3.5-turbo

    activities related to consuming beverages, particularly alcohol and other drinks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fold
    -0.73
    Enlarge
    -0.66
    auld
    -0.65
    ventures
    -0.64
    eq
    -0.64
    duction
    -0.64
     fold
    -0.62
    ifer
    -0.62
    immer
    -0.62
    immers
    -0.61
    POSITIVE LOGITS
     alcohol
    1.11
     champagne
    1.11
     wine
    1.08
     whiskey
    1.08
     vodka
    1.06
     whisky
    1.00
     booze
    0.99
     beer
    0.97
     soda
    0.95
    wine
    0.95
    Activations Density 0.121%

    No Known Activations