© 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. 10-RES-JB
    11. 12665
    Prev
    Next
    INDEX
    Explanations

    phrases related to alcohol consumption

    oai_token-act-pair · gpt-3.5-turbo

    references to alcohol consumption and drinking behaviors

    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
    yssey
    -0.81
    ventures
    -0.79
    translation
    -0.78
    iability
    -0.75
    answer
    -0.74
    idth
    -0.73
    ansion
    -0.73
    echo
    -0.72
    auld
    -0.71
    immer
    -0.69
    POSITIVE LOGITS
     alcohol
    1.39
     vodka
    1.17
     alcoholic
    1.17
     booze
    1.15
     opium
    1.09
     cigarettes
    1.09
     beer
    1.09
     marijuana
    1.09
     cannabis
    1.09
     whiskey
    1.07
    Activations Density 0.143%

    No Known Activations