© 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. 4-RES-JB
    11. 6882
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to nursing

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "nurse."

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

    No Comments

    Negative Logits
    çīĪ
    -0.88
    inations
    -0.81
    izons
    -0.74
     Ramadan
    -0.71
    ãĥĪ
    -0.68
    RFC
    -0.68
     Afgh
    -0.68
    urat
    -0.67
    inates
    -0.67
    obo
    -0.66
    POSITIVE LOGITS
    maid
    1.41
     practitioner
    1.37
     nurse
    1.03
     nurs
    1.02
     examiner
    1.01
     Nurs
    0.94
     practitioners
    0.93
     nurses
    0.90
     nursing
    0.88
     attendants
    0.77
    Activations Density 0.011%

    No Known Activations