© 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. 577
    Prev
    Next
    INDEX
    Explanations

    terms related to the drug "methamphetamine"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of methamphetamine and related compounds

    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
     Wolves
    -0.76
    DragonMagazine
    -0.75
     Dull
    -0.74
    Reviewer
    -0.74
    ç·
    -0.71
    Accessory
    -0.71
     Ashe
    -0.69
    velength
    -0.68
     Shape
    -0.67
     Pend
    -0.66
    POSITIVE LOGITS
    amphetamine
    1.10
    ilit
    1.09
     meth
    1.07
    oxy
    1.00
    inks
    0.97
     methamphetamine
    0.87
    hetamine
    0.85
    oglobin
    0.84
    urg
    0.81
    ugg
    0.81
    Activations Density 0.013%

    No Known Activations