© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10360
    Prev
    Next
    INDEX
    Explanations

    mentions of specific medical drugs or substances

    oai_token-act-pair · gpt-3.5-turbo

    medical terms related to drug substances and their effects

    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
    earth
    -0.82
    Earth
    -0.81
     Borders
    -0.74
     BaseType
    -0.74
     Layout
    -0.74
     Billboard
    -0.73
     Elm
    -0.72
     Eucl
    -0.72
    å£
    -0.71
    fitting
    -0.71
    POSITIVE LOGITS
     supplementation
    1.14
     sulf
    1.04
    amide
    0.96
    osis
    0.95
     overdose
    0.94
     toxicity
    0.93
     inhibitors
    0.93
     phosphate
    0.93
     chloride
    0.91
    phrine
    0.91
    Activations Density 0.081%

    No Known Activations