© 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. 1-RES-JB
    11. 14456
    Prev
    Next
    INDEX
    Explanations

    mentions of renewable energy

    oai_token-act-pair · gpt-3.5-turbo

    references to renewable energy sources and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.76
     Lew
    -0.75
    ãĥĥãĥī
    -0.75
     Foley
    -0.73
    nee
    -0.72
    ettings
    -0.70
     Kok
    -0.69
    sonian
    -0.69
    LY
    -0.69
     Kry
    -0.69
    POSITIVE LOGITS
     energy
    1.03
    jriwal
    0.94
    energy
    0.94
     efficiency
    0.92
     installations
    0.90
     equival
    0.86
     consumption
    0.85
     pollution
    0.84
     expenditure
    0.83
    utonium
    0.83
    Activations Density 0.022%

    No Known Activations