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. 4-RES-JB
    6. 3836
    Prev
    Next
    INDEX
    Explanations

    terms related to the controversial practice of hydraulic fracturing or "fracking."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hydraulic fracturing and drilling practices in the energy sector

    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
     Leilan
    -0.85
    BuyableInstoreAndOnline
    -0.78
    lihood
    -0.77
    epad
    -0.71
    ience
    -0.71
    ĪĴ
    -0.71
    pret
    -0.71
    luaj
    -0.70
    Def
    -0.69
    ulet
    -0.66
    POSITIVE LOGITS
     fracking
    1.10
     fracturing
    0.98
     wastewater
    0.86
     drilling
    0.84
     wells
    0.83
     rigs
    0.76
     pits
    0.75
    ulic
    0.75
     drill
    0.73
     chemicals
    0.72
    Activations Density 0.011%

    No Known Activations