© 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. 11-RES-JB
    11. 2385
    Prev
    Next
    INDEX
    Explanations

    mentions of specific universities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "University of" followed by various names

    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
     helic
    -0.77
    ividual
    -0.66
    together
    -0.66
    itiveness
    -0.65
     shortcuts
    -0.64
     toget
    -0.64
    ertodd
    -0.64
     disclaim
    -0.63
    chall
    -0.61
     shack
    -0.61
    POSITIVE LOGITS
     Pennsylvania
    1.31
     Illinois
    1.30
     Maryland
    1.29
     Connecticut
    1.27
     Notre
    1.27
     Michigan
    1.26
     Wisconsin
    1.26
     Cincinnati
    1.25
     Delaware
    1.24
     Nebraska
    1.24
    Activations Density 0.023%

    No Known Activations