© 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. 10-RES-JB
    11. 13700
    Prev
    Next
    INDEX
    Explanations

    elements related to fuel sources and types, including terms like coal, oil, natural gas, and uranium

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fossil fuels and energy sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onym
    -0.64
     Auditor
    -0.62
    arios
    -0.62
    76561
    -0.61
     Guarant
    -0.61
     outpost
    -0.60
     Imper
    -0.59
    istrate
    -0.59
    lihood
    -0.59
    minist
    -0.58
    POSITIVE LOGITS
     etc
    0.98
     or
    0.87
     dioxide
    0.85
    ,
    0.81
     equivalents
    0.79
    ;
    0.75
    oids
    0.74
    ®,
    0.73
    oline
    0.71
     and
    0.71
    Activations Density 0.260%

    No Known Activations