© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 14242
    Prev
    Next
    INDEX
    Explanations

    specific mentions of pharmacies or pharmacists

    oai_token-act-pair · gpt-3.5-turbo

    terms related to pharmacies and pharmacy professionals

    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
     Agenda
    -0.84
     Hornets
    -0.79
     Pelicans
    -0.78
     Geh
    -0.72
    hov
    -0.68
     Castro
    -0.68
     Trout
    -0.68
    TAG
    -0.68
    dar
    -0.67
     Dah
    -0.67
    POSITIVE LOGITS
     pharmac
    1.23
     pharmacy
    1.17
    aceutical
    1.17
     pharmacies
    1.14
     pharm
    1.04
     mathemat
    1.03
    ategory
    1.03
     chemist
    1.01
    istry
    0.98
    armac
    0.97
    Activations Density 0.010%

    No Known Activations