© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 3298
    Prev
    Next
    INDEX
    Explanations

    terms related to fracking and shale gas production

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to fracking and shale gas extraction

    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
    luaj
    -0.82
    ĪĴ
    -0.78
    boxing
    -0.77
    BuyableInstoreAndOnline
    -0.74
    ience
    -0.73
    reads
    -0.73
    é¾įåĸļ士
    -0.72
    ORPG
    -0.70
     Leilan
    -0.70
     Wong
    -0.69
    POSITIVE LOGITS
     fracturing
    1.18
     fracking
    1.16
     drilling
    1.11
     wastewater
    1.03
     wells
    0.97
     drill
    0.93
     drilled
    0.93
     shale
    0.93
    ulic
    0.84
     extraction
    0.81
    Activations Density 0.062%

    No Known Activations