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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4602
    Prev
    Next
    INDEX
    Explanations

    information related to energy production from renewable sources

    oai_token-act-pair · gpt-3.5-turbo

    references to renewable energy sources and their usage

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.85
     initials
    -0.80
     Breach
    -0.80
     plagiar
    -0.78
     Conspiracy
    -0.75
     IMAGES
    -0.75
     handwriting
    -0.74
     betray
    -0.74
     Poe
    -0.71
     Mock
    -0.71
    POSITIVE LOGITS
     electricity
    1.46
     renewable
    1.41
     fuels
    1.33
     renewables
    1.32
     wastewater
    1.25
     hydrogen
    1.25
     combustion
    1.23
     diesel
    1.23
     energy
    1.22
    electric
    1.22
    Activations Density 0.593%

    No Known Activations