© 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. 11-RES-JB
    11. 7683
    Prev
    Next
    INDEX
    Explanations

    information related to the generation of electricity and power capacity, including various forms such as wind, solar, and nuclear

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to energy production and capacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Journals
    -0.91
     phyl
    -0.81
    mone
    -0.75
     Shoes
    -0.73
     Decoder
    -0.72
    ĸļ
    -0.72
    Privacy
    -0.72
    gerald
    -0.71
     Blooming
    -0.70
    abilia
    -0.69
    POSITIVE LOGITS
     turbines
    1.37
     electricity
    1.36
     capacity
    1.34
     renewables
    1.34
     renewable
    1.29
    awatts
    1.18
     PV
    1.18
     turbine
    1.17
    MW
    1.15
     kW
    1.14
    Activations Density 0.305%

    No Known Activations