© 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. 2-RES-JB
    11. 1646
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "urn."

    oai_token-act-pair · gpt-3.5-turbo

    references to urns or related objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Suc
    -0.65
    Consumer
    -0.64
    aminer
    -0.64
     Solitaire
    -0.63
     Libre
    -0.63
    DonaldTrump
    -0.63
    enegger
    -0.61
     HERO
    -0.61
    sth
    -0.60
    EStream
    -0.59
    POSITIVE LOGITS
    urn
    1.44
    alia
    1.04
    eus
    0.95
    mentation
    0.91
    shire
    0.90
    ysis
    0.88
    sburg
    0.85
    alsh
    0.84
    ife
    0.82
    ault
    0.82
    Activations Density 0.007%

    No Known Activations