© 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. 0-RES-JB
    11. 16982
    Prev
    Next
    INDEX
    Explanations

    mentions of environmental pollution

    oai_token-act-pair · gpt-3.5-turbo

    references to pollution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fold
    -0.76
     Tact
    -0.75
     fold
    -0.69
    fold
    -0.68
    Ser
    -0.67
     Valiant
    -0.66
     Ft
    -0.66
    te
    -0.66
    heses
    -0.65
    vet
    -0.65
    POSITIVE LOGITS
     pollution
    3.50
     pollutants
    2.43
     polluted
    2.24
     pollut
    2.23
     emissions
    1.79
     emission
    1.57
     contamination
    1.55
     ozone
    1.47
     contaminants
    1.41
     congestion
    1.40
    Activations Density 0.014%

    No Known Activations