© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 8507
    Prev
    Next
    INDEX
    Explanations

    mentions of environmental contamination and health hazards

    oai_token-act-pair · gpt-3.5-turbo

    mentions of environmental hazards and their impacts on health and communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    joy
    -0.87
    rencies
    -0.80
    obook
    -0.78
     unification
    -0.77
    enfranch
    -0.77
     motivational
    -0.75
     simplify
    -0.75
    thood
    -0.75
     reunion
    -0.74
    olkien
    -0.73
    POSITIVE LOGITS
     contaminants
    1.79
     contamin
    1.77
     contamination
    1.74
     contaminated
    1.71
     groundwater
    1.62
     pollutants
    1.57
     arsenic
    1.55
     wastewater
    1.52
     pollut
    1.51
     toxins
    1.48
    Activations Density 0.567%

    No Known Activations