© 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. 2-RES-JB
    11. 23587
    Prev
    Next
    INDEX
    Explanations

    terms related to legal language and constitutional rights

    oai_token-act-pair · gpt-3.5-turbo

    references to legal concepts and amendments, particularly the Fourteenth Amendment's Equal Protection Clause

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     realise
    -0.76
    ufact
    -0.72
    icro
    -0.72
     Hai
    -0.72
    ongh
    -0.70
     Meth
    -0.70
     Seah
    -0.68
     [|
    -0.68
     highs
    -0.65
     Bild
    -0.65
    POSITIVE LOGITS
    Attorney
    1.15
     justices
    1.13
     attorneys
    1.01
     Amendment
    1.01
     unconstitutional
    1.00
     appellant
    0.99
     appellate
    0.98
     attorney
    0.97
     Scalia
    0.96
     Defendants
    0.95
    Activations Density 0.905%

    No Known Activations