© 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. 23704
    Prev
    Next
    INDEX
    Explanations

    mentions of various names, particularly "Katie" at varying levels of activation strength

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those named Katie and Julie

    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
    interstitial
    -0.95
    reed
    -0.81
    dfx
    -0.81
    lict
    -0.76
    enegger
    -0.76
    committee
    -0.75
    asks
    -0.74
    minist
    -0.74
    haps
    -0.73
    ribute
    -0.72
    POSITIVE LOGITS
     Katie
    1.00
     Nolan
    0.95
    Kat
    0.93
     Upton
    0.92
     Cour
    0.90
     Sue
    0.84
     Burton
    0.84
     Fallon
    0.84
     Holmes
    0.83
    Anne
    0.83
    Activations Density 0.006%

    No Known Activations