© 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. 11-RES-JB
    11. 4864
    Prev
    Next
    INDEX
    Explanations

    references to the Supreme Court of the United States

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Supreme Court

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptoms
    -0.80
    ku
    -0.74
    afort
    -0.68
     Typh
    -0.68
    rolet
    -0.67
    ufact
    -0.66
     DF
    -0.65
    river
    -0.64
     GF
    -0.63
    OPLE
    -0.62
    POSITIVE LOGITS
     justices
    1.46
     rulings
    1.11
     ruling
    1.06
    Justice
    1.04
     Justice
    1.04
     nominee
    0.97
    OTUS
    0.92
     upholding
    0.91
     precedent
    0.91
     decision
    0.90
    Activations Density 0.054%

    No Known Activations