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. 2-RES-JB
    6. 13277
    Prev
    Next
    INDEX
    Explanations

    narcotics-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to narcotics and associated behaviors or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eer
    -0.87
    EEE
    -0.78
    #$
    -0.77
    ffen
    -0.77
    OOL
    -0.75
    birds
    -0.74
    llan
    -0.73
    eers
    -0.73
    heit
    -0.73
    AKING
    -0.72
    POSITIVE LOGITS
    otics
    1.05
     narc
    1.04
     Narc
    1.03
    otic
    1.02
    issa
    0.93
    icit
    0.86
     commod
    0.86
    itionally
    0.84
     traffickers
    0.84
     narcotics
    0.84
    Activations Density 0.013%

    No Known Activations