© 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. 11-RES-JB
    11. 23828
    Prev
    Next
    INDEX
    Explanations

    terms related to the medical condition "diabetes"

    oai_token-act-pair · gpt-3.5-turbo

    references and discussions related to diabetes

    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
    bilt
    -0.86
    rative
    -0.78
    ership
    -0.75
    ateur
    -0.75
    ontent
    -0.74
    leon
    -0.73
    agame
    -0.71
    fman
    -0.71
    folk
    -0.68
    ovie
    -0.67
    POSITIVE LOGITS
     mell
    1.60
     complications
    0.97
     Mell
    0.96
     medication
    0.92
     diabetes
    0.90
     Diabetes
    0.89
     remission
    0.88
     medications
    0.88
     diagnosis
    0.86
     susceptibility
    0.84
    Activations Density 0.039%

    No Known Activations