© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 12936
    Prev
    Next
    INDEX
    Explanations

    references to renewable energy sources

    oai_token-act-pair · gpt-3.5-turbo

    references to renewable energy and its various aspects

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    uchi
    -0.71
    anova
    -0.68
    older
    -0.66
     Tsarnaev
    -0.65
    ourning
    -0.63
    pper
    -0.62
     assassinated
    -0.62
    acho
    -0.62
    much
    -0.61
    ifice
    -0.60
    POSITIVE LOGITS
     energy
    1.15
     fuels
    1.07
     energies
    1.05
    energy
    0.95
     renewable
    0.90
     fuel
    0.89
     electricity
    0.85
    issance
    0.80
     technologies
    0.78
    itures
    0.78
    Activations Density 0.035%

    No Known Activations