© 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. 15652
    Prev
    Next
    INDEX
    Explanations

    mentions of drug-related terms, particularly 'meth' and 'methamphetamine'

    oai_token-act-pair · gpt-3.5-turbo

    references to methamphetamine and related substances

    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
    BBC
    -0.75
    ç·
    -0.70
    DragonMagazine
    -0.69
    ORED
    -0.69
    Accessory
    -0.68
    ++++++++++++++++
    -0.68
    âĢ¢âĢ¢
    -0.68
    AMS
    -0.66
    WT
    -0.65
    ERC
    -0.65
    POSITIVE LOGITS
     meth
    1.45
     methamphetamine
    1.21
    amphetamine
    1.14
    ilit
    0.88
     Meth
    0.87
    oxy
    0.86
    inks
    0.85
     cocaine
    0.83
     overdoses
    0.81
    ħĭ
    0.81
    Activations Density 0.006%

    No Known Activations