© 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. 10-RES-JB
    11. 2831
    Prev
    Next
    INDEX
    Explanations

    names of retail companies and product-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to retail and shopping environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     treason
    -0.83
    ertodd
    -0.81
     advers
    -0.80
    ocument
    -0.71
     largeDownload
    -0.70
     tense
    -0.70
     transc
    -0.69
    REDACTED
    -0.68
     traumatic
    -0.68
    onomous
    -0.67
    POSITIVE LOGITS
     retailers
    1.52
     retailer
    1.50
    stores
    1.47
     brands
    1.41
     products
    1.41
     boutique
    1.40
     stores
    1.37
     Costco
    1.37
     suppliers
    1.37
     supermarkets
    1.37
    Activations Density 1.187%

    No Known Activations