© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4855
    Prev
    Next
    INDEX
    Explanations

    terms related to toxic substances and pollution in the context of environmental impact and health risks

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    issues related to environmental pollution and its impact on health

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Trials
    -0.69
    PDATE
    -0.69
    FM
    -0.66
    FTWARE
    -0.64
    ointed
    -0.63
    PN
    -0.63
    GBT
    -0.62
     Compass
    -0.62
    inelli
    -0.61
     NCT
    -0.60
    POSITIVE LOGITS
     contam
    1.42
     contamin
    1.31
     corro
    1.11
     penetrate
    1.10
     contaminated
    1.07
     escapes
    1.05
     accumulate
    1.05
     decom
    0.99
     carcin
    0.98
     migrate
    0.97
    Activations Density 0.234%

    No Known Activations