© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 23830
    Prev
    Next
    INDEX
    Explanations

    names of legal figures, particularly Supreme Court justices

    oai_token-act-pair · gpt-3.5-turbo

    references to justices and their affiliations 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 @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç
    -0.75
    orama
    -0.74
     Motorsport
    -0.70
     Mayhem
    -0.70
     Azerb
    -0.69
    resp
    -0.69
    tec
    -0.64
     EVENTS
    -0.64
     indo
    -0.63
    zb
    -0.63
    POSITIVE LOGITS
     Scalia
    1.28
     justices
    1.08
    Jud
    0.94
    otom
    0.90
     dissenting
    0.89
    blog
    0.86
     Gins
    0.85
     Sonia
    0.83
    OTUS
    0.82
    Court
    0.80
    Activations Density 0.095%

    No Known Activations