© 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. 2-RES-JB
    6. 17548
    Prev
    Next
    INDEX
    Explanations

    references to medical field, specifically focusing on terms related to medicine practices

    oai_token-act-pair · gpt-3.5-turbo

    references to the field of medicine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibilities
    -0.70
    aired
    -0.69
    stant
    -0.68
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.68
     sqor
    -0.67
    individual
    -0.65
    Vert
    -0.65
    utter
    -0.64
    local
    -0.64
    oir
    -0.64
    POSITIVE LOGITS
     medicine
    1.06
    istry
    0.90
     medicines
    0.87
    utics
    0.83
     pills
    0.82
     anesthesia
    0.78
     therapies
    0.77
     cures
    0.75
     inhal
    0.75
     dispens
    0.75
    Activations Density 0.009%

    No Known Activations