© 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. 4-RES-JB
    11. 20848
    Prev
    Next
    INDEX
    Explanations

    hyphenated words or phrases, possibly related to technology or commerce

    oai_token-act-pair · gpt-3.5-turbo

    references to e-commerce

    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
    ulhu
    -0.77
    eele
    -0.72
     Rivals
    -0.67
     AVG
    -0.67
     Starr
    -0.67
     Cassidy
    -0.67
    wcs
    -0.65
     ingred
    -0.64
     Twain
    -0.62
    Ô
    -0.61
    POSITIVE LOGITS
    series
    1.09
    expression
    1.07
    commerce
    1.03
    mails
    1.00
    meter
    0.99
    edition
    0.94
    service
    0.94
    govern
    0.93
    shaped
    0.92
    mail
    0.91
    Activations Density 0.050%

    No Known Activations