© 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 EvalsExportsinterp-engineNEWAPI 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. 5747
    Prev
    Next
    INDEX
    Explanations

    references to medication or drugs, specifically focusing on pills

    oai_token-act-pair · gpt-3.5-turbo

    mentions of pills and medication

    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
     Bucc
    -0.75
    CTV
    -0.72
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.71
    REM
    -0.68
    Published
    -0.68
    BAT
    -0.68
    Reviewer
    -0.67
    ORN
    -0.66
    rian
    -0.66
    Topics
    -0.65
    POSITIVE LOGITS
     pills
    1.36
     pill
    0.99
    autions
    0.94
    hetamine
    0.93
    terday
    0.92
    creen
    0.91
    pill
    0.91
     aspirin
    0.89
    ilon
    0.89
    ules
    0.88
    Activations Density 0.012%

    No Known Activations