© 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. 1-RES-JB
    11. 21576
    Prev
    Next
    INDEX
    Explanations

    references to nurses with varying contexts including their actions, backgrounds, and relationships

    oai_token-act-pair · gpt-3.5-turbo

    mentions of nursing professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.83
    RFC
    -0.71
    Ùħ
    -0.69
    اÙĦ
    -0.68
    arta
    -0.68
    AIN
    -0.67
    inations
    -0.67
    urat
    -0.67
    à
    -0.65
    adr
    -0.65
    POSITIVE LOGITS
     practitioner
    1.27
    maid
    1.25
     nurse
    1.15
     examiner
    0.98
     nurs
    0.96
     nurses
    0.94
     Nurs
    0.91
     nursing
    0.91
     Nurse
    0.86
     practitioners
    0.86
    Activations Density 0.007%

    No Known Activations