© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 2917
    Prev
    Next
    INDEX
    Explanations

    word related to medical treatments or solutions, particularly cures for different conditions, symptoms, or diseases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cures and treatments for diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ideshow
    -0.69
    adden
    -0.68
     Huss
    -0.66
    ramid
    -0.64
     Fired
    -0.64
     JO
    -0.63
     OW
    -0.63
    opers
    -0.62
     guiActiveUnfocused
    -0.62
    ardy
    -0.62
    POSITIVE LOGITS
     cure
    0.99
    nces
    0.94
     cures
    0.91
    rers
    0.76
    tt
    0.75
    nce
    0.75
    philis
    0.75
     malaria
    0.75
    ts
    0.74
    crow
    0.73
    Activations Density 0.028%

    No Known Activations