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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3298
    Prev
    Next
    INDEX
    Explanations

    words related to medical treatments and therapies

    oai_token-act-pair · gpt-3.5-turbo

    terminologies related to medical treatments and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.90
    ĸļ
    -0.79
    sbm
    -0.78
    isSpecialOrderable
    -0.78
    fman
    -0.77
    soType
    -0.75
    displayText
    -0.74
    ramid
    -0.68
    Catalog
    -0.67
     Transcript
    -0.66
    POSITIVE LOGITS
     ailments
    1.38
     epilepsy
    1.38
     arthritis
    1.32
     nausea
    1.29
     patients
    1.26
     diseases
    1.25
     migraine
    1.24
     illnesses
    1.22
     insomnia
    1.21
     headaches
    1.20
    Activations Density 0.203%

    No Known Activations