© 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. 11-RES-JB
    11. 20426
    Prev
    Next
    INDEX
    Explanations

    information related to drunk driving

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with intoxication and impaired driving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.79
    Downloadha
    -0.72
    CVE
    -0.71
    TPP
    -0.71
    MpServer
    -0.68
    pta
    -0.67
     JPM
    -0.64
    isite
    -0.62
    psons
    -0.62
    profits
    -0.61
    POSITIVE LOGITS
    ards
    1.09
     driving
    0.97
    driving
    0.94
    ard
    0.94
     Driving
    0.90
     drunk
    0.88
    cohol
    0.87
     manslaughter
    0.86
    ewitness
    0.85
     beverages
    0.83
    Activations Density 0.076%

    No Known Activations