© 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. 6-RES-JB
    11. 9498
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions, specifically ulcers

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with ulcers and related medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Butterfly
    -0.74
     Covenant
    -0.72
     Continued
    -0.67
     Beyond
    -0.65
     Stafford
    -0.64
     Triumph
    -0.64
     Heritage
    -0.63
     Juliet
    -0.63
     Adventures
    -0.62
     Carbuncle
    -0.61
    POSITIVE LOGITS
    monary
    1.02
    terior
    1.01
    gur
    0.95
    umn
    0.92
    ricanes
    0.89
    cer
    0.89
    ftime
    0.86
    aiman
    0.86
    cery
    0.85
    phies
    0.85
    Activations Density 0.027%

    No Known Activations