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

    Neuronpedia

    APICircuit 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. 10-RES-JB
    6. 13169
    Prev
    Next
    INDEX
    Explanations

    terms related to the legalization, usage, and opinions about marijuana

    oai_token-act-pair · gpt-3.5-turbo

    information related to the laws and regulations surrounding marijuana use and possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Titanic
    -1.11
     pengu
    -0.87
    MpServer
    -0.85
    selage
    -0.84
    leigh
    -0.84
     Hebdo
    -0.84
    yss
    -0.84
    nces
    -0.78
     condol
    -0.78
     Orchestra
    -0.77
    POSITIVE LOGITS
     marijuana
    2.03
     cannabis
    1.98
     Marijuana
    1.97
     Cannabis
    1.97
    arijuana
    1.96
     dispensaries
    1.91
     legalization
    1.86
     THC
    1.85
     dispensary
    1.78
     cannabinoids
    1.73
    Activations Density 0.414%

    No Known Activations