© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 19285
    Prev
    Next
    INDEX
    Explanations

    e-commerce platforms and online payment services

    oai_token-act-pair · gpt-3.5-turbo

    references to online marketplaces and payment platforms

    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
     trained
    -0.71
     plant
    -0.68
     cannon
    -0.67
     mel
    -0.65
    ãĢ
    -0.65
    ow
    -0.62
     cant
    -0.61
    ress
    -0.61
    cess
    -0.60
    ~~~~~~~~
    -0.60
    POSITIVE LOGITS
     eBay
    3.74
     Craigslist
    2.60
     Etsy
    2.51
     PayPal
    2.38
     Yelp
    2.10
     Airbnb
    2.08
     LinkedIn
    1.82
     Flickr
    1.67
     Dropbox
    1.67
     Alibaba
    1.66
    Activations Density 0.013%

    No Known Activations