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. 6-RES-JB
    6. 16267
    Prev
    Next
    INDEX
    Explanations

    words related to fracking and shale gas production

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hydraulic fracturing 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 @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leilan
    -0.84
    ĪĴ
    -0.78
    ience
    -0.77
    luaj
    -0.75
    BuyableInstoreAndOnline
    -0.73
     Smile
    -0.72
    ership
    -0.72
     Krug
    -0.71
    epad
    -0.70
    SHIP
    -0.69
    POSITIVE LOGITS
     fracking
    1.12
     fracturing
    1.09
     drilling
    0.93
     drill
    0.85
     wells
    0.84
     wastewater
    0.81
    ulic
    0.79
     shale
    0.79
     rigs
    0.76
     pits
    0.74
    Activations Density 0.033%

    No Known Activations