© 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. 11-RES-JB
    11. 1516
    Prev
    Next
    INDEX
    Explanations

    events or actions related to medical situations, such as hospital visits and diagnoses

    oai_token-act-pair · gpt-3.5-turbo

    references to hospital visits and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.81
     Tradable
    -0.76
    skirts
    -0.73
    idable
    -0.67
    enary
    -0.66
    obook
    -0.65
    deals
    -0.65
    xual
    -0.64
     enforce
    -0.64
    Political
    -0.64
    POSITIVE LOGITS
    Doctors
    1.91
     doctors
    1.87
     surgeons
    1.76
     Doctors
    1.71
     Surgery
    1.63
     surgery
    1.62
     chemotherapy
    1.54
     anesthesia
    1.50
     neurolog
    1.47
     doctor
    1.47
    Activations Density 0.583%

    No Known Activations