© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 15415
    Prev
    Next
    INDEX
    Explanations

    words related to different types of pollution, including both specific types of pollution and broader concepts like environmental pollution

    oai_token-act-pair · gpt-3.5-turbo

    words related to environmental pollution and its impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndra
    -0.73
    tell
    -0.71
    coni
    -0.70
    beit
    -0.67
    orian
    -0.67
    canon
    -0.67
    phabet
    -0.67
    kell
    -0.66
    llan
    -0.66
    pha
    -0.66
    POSITIVE LOGITS
     poisoning
    1.06
     pollution
    0.99
     polluted
    0.94
     contamin
    0.91
     contamination
    0.89
     contaminated
    0.89
     spills
    0.88
     fumes
    0.86
     exposures
    0.84
     inhal
    0.84
    Activations Density 0.078%

    No Known Activations