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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 20306
    Prev
    Next
    INDEX
    Explanations

    terms related to different types of energy sources, such as renewable energy, coal, natural gas, nuclear power, and hydroelectric power

    oai_token-act-pair · gpt-3.5-turbo

    terms related to energy sources and their environmental 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
    ĸļ
    -1.01
     Spiel
    -0.82
    verbal
    -0.77
     etiquette
    -0.76
     handwriting
    -0.76
    atched
    -0.76
     Scholarship
    -0.75
     Tatt
    -0.75
     Phar
    -0.75
     Poster
    -0.75
    POSITIVE LOGITS
     renewable
    1.59
     electricity
    1.56
     renewables
    1.55
     combustion
    1.54
     hydrogen
    1.50
     diesel
    1.49
     fuels
    1.47
     coal
    1.42
     biomass
    1.42
     energy
    1.39
    Activations Density 0.847%

    No Known Activations