© 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. 9-RES-JB
    11. 19478
    Prev
    Next
    INDEX
    Explanations

    medical and health-related terms and conditions, as well as instructions for healthcare actions

    oai_token-act-pair · gpt-3.5-turbo

    medical conditions and related diagnostic tests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     damned
    -0.78
     meme
    -0.77
     sentient
    -0.74
     memes
    -0.72
     laureate
    -0.71
    fuck
    -0.71
    Fuck
    -0.70
    Evil
    -0.69
     fuck
    -0.69
     dudes
    -0.69
    POSITIVE LOGITS
     Residential
    0.99
     Your
    0.95
     Choose
    0.94
     eligibility
    0.92
     Depending
    0.92
     Procedures
    0.91
    requently
    0.91
     Regulations
    0.91
     broch
    0.89
     Information
    0.88
    Activations Density 0.740%

    No Known Activations