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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 3941
    Prev
    Next
    INDEX
    Explanations

    words related to alcoholic beverages, specifically wine and champagne

    oai_token-act-pair · gpt-3.5-turbo

    references to wine and alcoholic beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WATCHED
    -0.79
    ļé
    -0.72
    rals
    -0.70
     advers
    -0.68
    Tur
    -0.67
     Tracking
    -0.67
    ospace
    -0.64
    anmar
    -0.62
    erenn
    -0.61
    idable
    -0.61
    POSITIVE LOGITS
     bottles
    1.12
     tasting
    1.11
     bottle
    1.04
     tast
    1.03
     drinkers
    1.01
     Bottle
    0.96
     flowed
    0.92
     wine
    0.87
     vinegar
    0.85
     flask
    0.85
    Activations Density 0.061%

    No Known Activations