© 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. 10-RES-JB
    11. 3148
    Prev
    Next
    INDEX
    Explanations

    references to drinks, specifically alcoholic beverages

    oai_token-act-pair · gpt-3.5-turbo

    terms related to drinking water

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sharif
    -0.86
     notch
    -0.73
    cephal
    -0.65
     Parenthood
    -0.63
    asia
    -0.61
     router
    -0.60
     Postal
    -0.60
     Payton
    -0.60
    ansion
    -0.60
    ":["
    -0.59
    POSITIVE LOGITS
    cohol
    1.22
    water
    1.17
     alcohol
    1.13
     bottles
    1.12
     beverages
    1.07
     brewed
    1.05
     drinking
    1.04
     drinkers
    1.03
     beverage
    0.99
     water
    0.99
    Activations Density 0.053%

    No Known Activations