© 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. 4-RES-JB
    11. 24082
    Prev
    Next
    INDEX
    Explanations

    medical terms and actions performed by doctors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of doctors

    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
     Territories
    -0.97
    uble
    -0.73
    âĸ¬
    -0.69
    Bush
    -0.69
    ptions
    -0.67
    Operation
    -0.67
    FACE
    -0.67
    campaign
    -0.66
    lust
    -0.66
    Campaign
    -0.66
    POSITIVE LOGITS
     doctor
    0.85
     doctors
    0.85
     diagnose
    0.84
     treating
    0.83
     care
    0.83
     diagn
    0.82
     diagnosed
    0.80
     practitioner
    0.80
    aret
    0.79
    icians
    0.78
    Activations Density 0.017%

    No Known Activations