© 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 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. 3-RES-JB
    11. 5423
    Prev
    Next
    INDEX
    Explanations

    medical symptoms

    oai_token-act-pair · gpt-3.5-turbo

    references to symptoms of various medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISO
    -0.70
    yss
    -0.69
    oir
    -0.66
    olan
    -0.63
    atan
    -0.62
    berman
    -0.60
    atography
    -0.60
    cé
    -0.60
    erker
    -0.59
     Aerospace
    -0.58
    POSITIVE LOGITS
    ptoms
    1.52
     Symptoms
    1.26
     symptoms
    1.23
     symptom
    0.89
     worsen
    0.86
    igue
    0.85
     ailments
    0.85
    igmatic
    0.81
    olutions
    0.80
    âĶģ
    0.79
    Activations Density 0.012%

    No Known Activations