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. 0-RES-JB
    6. 4313
    Prev
    Next
    INDEX
    Explanations

    terms related to hydraulic fracturing, specifically identifying 'fracking' within text and related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the fracking industry and shale gas production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tan
    -0.71
     Ace
    -0.69
    master
    -0.68
     Cy
    -0.67
    antam
    -0.66
     Tip
    -0.64
     Lump
    -0.62
    hered
    -0.62
    sense
    -0.61
     Mat
    -0.61
    POSITIVE LOGITS
     fracking
    3.61
     shale
    2.16
     fracturing
    2.13
     drilling
    1.73
     hydraulic
    1.67
     GMOs
    1.38
     methane
    1.36
     groundwater
    1.34
     pipelines
    1.30
     renewables
    1.30
    Activations Density 0.021%

    No Known Activations