© 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. 11-RES-JB
    11. 2861
    Prev
    Next
    INDEX
    Explanations

    references to historical figures (specifically the Founding Fathers of the United States) and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the Founding Fathers or foundational concepts of the United States

    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
    rar
    -0.76
    eeper
    -0.67
    aspx
    -0.61
     forthcoming
    -0.61
     upcoming
    -0.60
    asma
    -0.58
    Staff
    -0.57
    ILA
    -0.56
     vacancies
    -0.55
     unexpectedly
    -0.54
    POSITIVE LOGITS
     centuries
    1.17
     eras
    1.10
     millennia
    1.04
     civilizations
    0.99
     Era
    0.98
     generations
    0.96
     ancestors
    0.94
     1900
    0.91
     era
    0.91
     slavery
    0.90
    Activations Density 0.455%

    No Known Activations