© 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. 6-RES-JB
    11. 7987
    Prev
    Next
    INDEX
    Explanations

    mentions of drugs and medical treatments and their effectiveness or approval status

    oai_token-act-pair · gpt-3.5-turbo

    mentions of drugs and their medical usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pie
    -0.85
    Layout
    -0.80
     Cind
    -0.79
    Writ
    -0.78
     Spaces
    -0.77
     Libraries
    -0.74
     Pension
    -0.74
    selage
    -0.74
     Chess
    -0.74
    Marx
    -0.73
    POSITIVE LOGITS
     therapeutic
    1.35
     medication
    1.33
     therape
    1.32
     medications
    1.30
     therapies
    1.25
     treatments
    1.23
     administered
    1.21
     drugs
    1.21
     dosage
    1.19
     analges
    1.19
    Activations Density 0.395%

    No Known Activations