© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20609
    Prev
    Next
    INDEX
    Explanations

    words related to urns

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 'urn' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aminer
    -0.90
     Beir
    -0.80
     Rafael
    -0.73
     lag
    -0.71
    agos
    -0.71
    DonaldTrump
    -0.69
    omsky
    -0.69
    ploma
    -0.65
    Domin
    -0.63
    Magikarp
    -0.61
    POSITIVE LOGITS
    s
    1.04
    ments
    0.92
    shire
    0.89
    sburg
    0.89
    ing
    0.88
    mentation
    0.86
    ished
    0.85
    iture
    0.85
    ships
    0.85
    ezvous
    0.83
    Activations Density 0.047%

    No Known Activations