© 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. 1-RES-JB
    11. 5158
    Prev
    Next
    INDEX
    Explanations

    mentions of intoxication or being drunk

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "drunk."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AUT
    -0.73
    EVA
    -0.73
     Flavoring
    -0.71
    ERO
    -0.67
    issues
    -0.67
    CVE
    -0.66
    /+
    -0.66
    ETA
    -0.66
    ocol
    -0.64
    tracks
    -0.63
    POSITIVE LOGITS
     drunk
    1.28
     drinking
    1.00
    ards
    0.97
     drinkers
    0.96
     underage
    0.92
     binge
    0.88
     intoxicated
    0.85
     Drinking
    0.85
     alcohol
    0.85
    cohol
    0.84
    Activations Density 0.006%

    No Known Activations