Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 12957
    Prev
    Next
    INDEX
    Explanations

    terms related to fracking and shale gas extraction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the extraction and production of fossil fuels, particularly associated with shale gas and hydraulic fracturing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wong
    -0.83
     Acer
    -0.80
     Asus
    -0.80
    endars
    -0.75
    boxing
    -0.74
    verbal
    -0.74
    usc
    -0.72
    reads
    -0.72
     Dumbledore
    -0.71
    isf
    -0.71
    POSITIVE LOGITS
     shale
    1.36
     fracking
    1.35
     drilling
    1.34
     wastewater
    1.26
     oil
    1.26
     pipeline
    1.23
     pipelines
    1.21
     extraction
    1.18
     sands
    1.08
     Pipeline
    1.07
    Activations Density 0.284%

    No Known Activations