© 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. 11-RES-JB
    11. 16598
    Prev
    Next
    INDEX
    Explanations

    references to US Supreme Court Justices

    oai_token-act-pair · gpt-3.5-turbo

    references to justices and their opinions in a legal context

    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
    ramid
    -0.74
    FTWARE
    -0.70
    tenance
    -0.69
    ghai
    -0.69
    wx
    -0.69
    wagen
    -0.67
     Mayhem
    -0.67
    bsite
    -0.66
     Kickstarter
    -0.66
     Pyramid
    -0.66
    POSITIVE LOGITS
     Scalia
    1.50
    otom
    1.33
     dissent
    1.32
     Gins
    1.28
     dissenting
    1.26
     Sonia
    1.05
     justices
    1.05
     Elena
    1.02
     Gorsuch
    1.02
     diss
    1.00
    Activations Density 0.134%

    No Known Activations