© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 4994
    Prev
    Next
    INDEX
    Explanations

    various types of alcoholic beverages, such as bourbon, whiskey, rye, and Scotch

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bourbon and whiskey

    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
    ding
    -0.83
    ularity
    -0.80
    lez
    -0.80
     Parenthood
    -0.78
    ULAR
    -0.77
    ospace
    -0.73
     Submission
    -0.72
     Tracking
    -0.70
    lihood
    -0.68
    dy
    -0.68
    POSITIVE LOGITS
     whisky
    1.20
     whiskey
    1.17
     liquor
    1.07
    wine
    0.98
     distilled
    0.95
    cohol
    0.94
     beverage
    0.91
     vinegar
    0.91
     tasting
    0.91
     Whis
    0.90
    Activations Density 0.035%

    No Known Activations