© 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. 0-RES-JB
    11. 1737
    Prev
    Next
    INDEX
    Explanations

    the name "Scalia"

    oai_token-act-pair · gpt-3.5-turbo

    references to Justice Antonin Scalia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GB
    -0.65
    glers
    -0.65
     routes
    -0.64
    MD
    -0.64
     Channel
    -0.64
     inst
    -0.64
    bb
    -0.63
     kit
    -0.63
     mobile
    -0.62
     effort
    -0.62
    POSITIVE LOGITS
     Scalia
    3.88
     Gorsuch
    2.10
     Gins
    1.47
     Grassley
    1.36
     justices
    1.27
     Coulter
    1.25
     Rove
    1.23
     Limbaugh
    1.23
     Hannity
    1.20
     ALEC
    1.20
    Activations Density 0.022%

    No Known Activations