© 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. 10-RES-JB
    11. 6417
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to environmental impact and carbon emissions

    oai_token-act-pair · gpt-3.5-turbo

    references to greenhouse gas emissions and their impact from various countries

    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
     honors
    -0.82
    ĸļ
    -0.82
     courthouse
    -0.81
     regulars
    -0.80
     decorated
    -0.77
     misdemeanor
    -0.77
     SWAT
    -0.76
     honoring
    -0.76
     honor
    -0.74
     unmarked
    -0.74
    POSITIVE LOGITS
    India
    1.33
    Econom
    1.31
     OECD
    1.26
     forecasts
    1.25
    Economic
    1.22
    China
    1.14
    Global
    1.10
     forecast
    1.08
    Indust
    1.06
    Energy
    1.05
    Activations Density 0.856%

    No Known Activations