© 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. 0-RES-JB
    11. 1198
    Prev
    Next
    INDEX
    Explanations

    terms related to medical prescriptions and drugs

    oai_token-act-pair · gpt-3.5-turbo

    references to prescription medications and their necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bil
    -0.80
     Animation
    -0.78
    Ball
    -0.73
    ev
    -0.71
    birds
    -0.70
    boss
    -0.70
     gather
    -0.68
     Lamb
    -0.68
     Oo
    -0.67
     Chaos
    -0.67
    POSITIVE LOGITS
     prescription
    3.75
     prescriptions
    3.04
     prescribing
    1.75
     medication
    1.59
     medications
    1.56
     pharmaceutical
    1.49
     pharmacy
    1.49
     pharmacies
    1.48
     prescribe
    1.48
     prescribed
    1.43
    Activations Density 0.007%

    No Known Activations