© 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. 1-RES-JB
    11. 21935
    Prev
    Next
    INDEX
    Explanations

    chemical substances

    oai_token-act-pair · gpt-3.5-turbo

    references to hazardous 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 @ 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
    Interview
    -0.77
    chron
    -0.74
    iak
    -0.70
    Had
    -0.69
    ership
    -0.67
    Seg
    -0.67
    zzi
    -0.66
    mn
    -0.65
     Cardinals
    -0.65
    fm
    -0.64
    POSITIVE LOGITS
     chemicals
    1.37
     substances
    1.11
     additives
    1.05
     compounds
    1.03
     toxins
    1.01
     pollutants
    1.01
     fumes
    1.00
     chlorine
    0.98
     ingred
    0.96
     chemist
    0.96
    Activations Density 0.011%

    No Known Activations