© 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. 6-RES-JB
    11. 3564
    Prev
    Next
    INDEX
    Explanations

    words related to alcohol consumption and its consequences, specifically focusing on instances of drunkenness

    oai_token-act-pair · gpt-3.5-turbo

    references to intoxication, particularly related to being drunk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.88
     JPM
    -0.78
     Flavoring
    -0.75
    akeru
    -0.72
    ILA
    -0.71
    DonaldTrump
    -0.70
    isite
    -0.70
    adr
    -0.68
    metics
    -0.67
    ocol
    -0.66
    POSITIVE LOGITS
     drunk
    1.00
    ards
    0.95
    bott
    0.93
     drinking
    0.88
     underage
    0.84
    cohol
    0.83
    ness
    0.82
     manslaughter
    0.80
     alcohol
    0.79
     binge
    0.79
    Activations Density 0.029%

    No Known Activations