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. 0-RES-JB
    6. 1000
    Prev
    Next
    INDEX
    Explanations

    terms related to the legalization of marijuana, specifically focusing on the word "legalize."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the legalization of marijuana

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shack
    -0.72
     di
    -0.67
     arte
    -0.67
     cad
    -0.64
    oir
    -0.64
     Fleet
    -0.63
     Cats
    -0.63
    oman
    -0.62
     Channel
    -0.62
    tt
    -0.61
    POSITIVE LOGITS
     legalization
    3.26
     legalizing
    3.17
     legalize
    3.13
     legalized
    3.03
     decriminal
    2.61
     Marijuana
    1.77
    arijuana
    1.73
     Cannabis
    1.61
     marijuana
    1.58
    legal
    1.56
    Activations Density 0.022%

    No Known Activations