© 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. 11021
    Prev
    Next
    INDEX
    Explanations

    references to toxic chemicals

    oai_token-act-pair · gpt-3.5-turbo

    references to harmful chemicals and their impact on health and the environment

    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
    ership
    -0.91
    doms
    -0.82
    Fal
    -0.73
    stad
    -0.72
    itia
    -0.71
    shire
    -0.71
    esan
    -0.70
    resents
    -0.69
    heit
    -0.69
    noon
    -0.68
    POSITIVE LOGITS
     chemicals
    1.15
     additives
    1.02
     chemically
    1.01
     substances
    1.00
     compounds
    1.00
     oxide
    0.95
     dioxide
    0.95
     chlorine
    0.91
     toxins
    0.91
     pollutants
    0.90
    Activations Density 0.014%

    No Known Activations