© 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. 0-RES-JB
    11. 18128
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "marijuana"

    oai_token-act-pair · gpt-3.5-turbo

    references to marijuana and its related legal, medical, and social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ao
    -0.80
    oir
    -0.76
    itect
    -0.67
    egu
    -0.66
     Gir
    -0.66
    Arch
    -0.65
     Lag
    -0.64
    antage
    -0.64
     Ik
    -0.64
    anship
    -0.64
    POSITIVE LOGITS
     marijuana
    3.49
     Marijuana
    3.18
    arijuana
    2.95
     cannabis
    2.83
     Cannabis
    2.62
     THC
    2.04
     cannabinoid
    2.00
     cannabinoids
    1.98
     hemp
    1.94
     weed
    1.89
    Activations Density 0.016%

    No Known Activations