Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18223
    Prev
    Next
    INDEX
    Explanations

    mentions of the drug "meth" or "methamphetamine."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to methamphetamine and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.82
     Dull
    -0.76
     Wolves
    -0.75
    Accessory
    -0.73
    Reviewer
    -0.72
    velength
    -0.72
    ç·
    -0.70
     Vector
    -0.70
     Ashe
    -0.69
    ORED
    -0.67
    POSITIVE LOGITS
     meth
    1.18
    amphetamine
    1.15
    ilit
    1.03
    oxy
    1.02
     methamphetamine
    0.95
    hetamine
    0.92
    inks
    0.91
    oglobin
    0.84
    imes
    0.82
     cocaine
    0.81
    Activations Density 0.012%

    No Known Activations