© 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. 8-RES-JB
    11. 2539
    Prev
    Next
    INDEX
    Explanations

    words related to medical terminology and health-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to medical treatments or procedures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Instruments
    -0.77
    enance
    -0.73
    ĸļ
    -0.70
    ruary
    -0.64
    INGTON
    -0.64
     anonymity
    -0.62
     initials
    -0.62
    enegger
    -0.61
     retri
    -0.61
     attribution
    -0.61
    POSITIVE LOGITS
    lect
    0.98
    ft
    0.97
    vered
    0.96
    ques
    0.94
    xt
    0.93
    ffect
    0.92
    utical
    0.91
    ople
    0.91
    que
    0.90
    tes
    0.89
    Activations Density 0.132%

    No Known Activations