© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 2272
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to environmental pollution

    oai_token-act-pair · gpt-3.5-turbo

    references to pollution and its effects

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

    No Comments

    Negative Logits
    tell
    -0.79
    orian
    -0.77
    tre
    -0.74
    CHA
    -0.73
    beit
    -0.72
    ndra
    -0.71
    Bone
    -0.71
    laus
    -0.70
    lis
    -0.70
    bable
    -0.70
    POSITIVE LOGITS
     pollution
    1.06
     emissions
    0.87
     pollutants
    0.86
     pollut
    0.85
     dioxide
    0.84
     spew
    0.79
     fumes
    0.79
     contamin
    0.78
     polluted
    0.78
     poisoning
    0.76
    Activations Density 0.008%

    No Known Activations