© 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. 6-RES-JB
    11. 11786
    Prev
    Next
    INDEX
    Explanations

    chemical compound names, especially ones related to medication

    oai_token-act-pair · gpt-3.5-turbo

    pharmaceutical terms and names of drugs

    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
    å£
    -0.82
     BaseType
    -0.81
    Fi
    -0.78
    Earth
    -0.75
     Polk
    -0.73
     Vec
    -0.71
    Aust
    -0.71
    earth
    -0.69
     Elm
    -0.68
     Liang
    -0.67
    POSITIVE LOGITS
     supplementation
    1.09
     phosphate
    1.09
    amide
    1.06
     sulf
    0.99
     overdose
    0.97
     toxicity
    0.95
     chloride
    0.95
     gluc
    0.94
     capsules
    0.93
     poisoning
    0.92
    Activations Density 0.109%

    No Known Activations