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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 6382
    Prev
    Next
    INDEX
    Explanations

    words related to containers or vessels, specifically "urn"

    oai_token-act-pair · gpt-3.5-turbo

    references to urns or similar objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aminer
    -0.72
    print
    -0.69
    Consumer
    -0.69
    DonaldTrump
    -0.66
    Spoiler
    -0.65
    word
    -0.64
    BIL
    -0.62
     Solitaire
    -0.60
    ³³³³³³³³³³³³³³³³
    -0.60
     lag
    -0.59
    POSITIVE LOGITS
    urn
    1.19
    eus
    0.89
    iture
    0.87
    mentation
    0.87
    alia
    0.87
    sburg
    0.86
    ysis
    0.86
    ezvous
    0.85
    shire
    0.84
    ing
    0.81
    Activations Density 0.008%

    No Known Activations