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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24156
    Prev
    Next
    INDEX
    Explanations

    medical conditions or illnesses

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of illnesses

    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
     compr
    -0.69
    cycl
    -0.65
     drilled
    -0.65
     miniature
    -0.65
     bloc
    -0.61
     kinetic
    -0.61
     bumper
    -0.60
     tentative
    -0.60
     counted
    -0.60
     borrowed
    -0.60
    POSITIVE LOGITS
     illness
    1.07
    imei
    0.93
     illnesses
    0.92
    ptoms
    0.91
    nesses
    0.87
    igue
    0.85
     sickness
    0.82
    uminati
    0.81
    ousing
    0.80
    adelphia
    0.78
    Activations Density 0.015%

    No Known Activations