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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 12456
    Prev
    Next
    INDEX
    Explanations

    terms related to drugs, specifically MDMA and related substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to psychoactive substances, particularly MDMA and ecstasy

    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
    beard
    -0.76
    Eat
    -0.71
    NEY
    -0.71
    ament
    -0.70
    onal
    -0.70
    lest
    -0.69
     Doodle
    -0.69
    bid
    -0.68
     Einstein
    -0.67
    earth
    -0.66
    POSITIVE LOGITS
    stasy
    1.68
    amphetamine
    1.21
     ecstasy
    1.17
    amines
    1.04
     confir
    0.95
     MDMA
    0.88
    eger
    0.82
     Drugs
    0.82
     methamphetamine
    0.81
     drugs
    0.81
    Activations Density 0.014%

    No Known Activations