© 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. 14468
    Prev
    Next
    INDEX
    Explanations

    words related to the field of orthopedics

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to orthopedics and surgeries

    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
    ITED
    -0.87
    hips
    -0.82
    ========
    -0.78
    KER
    -0.76
    IRO
    -0.75
    Connector
    -0.74
    Package
    -0.71
    ource
    -0.70
    KING
    -0.70
    ÙIJ
    -0.70
    POSITIVE LOGITS
     orth
    1.34
    ĺħ
    1.09
     mathemat
    1.06
    entimes
    1.02
    ©¶æ
    1.01
     metic
    1.01
     isot
    0.99
     Orth
    0.98
    ŃĶ
    0.97
     ende
    0.97
    Activations Density 0.010%

    No Known Activations