© 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. 4-RES-JB
    11. 19826
    Prev
    Next
    INDEX
    Explanations

    mentions of oil drilling activities and related events or entities

    oai_token-act-pair · gpt-3.5-turbo

    topics related to oil drilling incidents and their consequences

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

    No Comments

    Negative Logits
    ¥µ
    -0.76
    quickShipAvailable
    -0.73
    endars
    -0.72
    VID
    -0.70
    isphere
    -0.70
     Fn
    -0.69
    izophren
    -0.68
    ãĥ´ãĤ¡
    -0.67
    verbal
    -0.67
    é¾įåĸļ士
    -0.67
    POSITIVE LOGITS
     dams
    1.14
     pipelines
    1.02
     drilling
    1.01
     stockp
    0.99
     wastewater
    0.98
     offshore
    0.94
     dred
    0.92
     pipeline
    0.90
     uranium
    0.90
     leasing
    0.89
    Activations Density 0.238%

    No Known Activations