© 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. 3-RES-JB
    11. 580
    Prev
    Next
    INDEX
    Explanations

    references to people named Katie

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Katie" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.84
    dfx
    -0.80
    lict
    -0.78
    committee
    -0.77
    pmwiki
    -0.77
    netflix
    -0.77
    asks
    -0.75
    reed
    -0.74
    enegger
    -0.74
    ional
    -0.73
    POSITIVE LOGITS
     Cour
    0.94
    Kat
    0.94
     Katie
    0.90
     Upton
    0.89
     Holmes
    0.88
     Nolan
    0.87
     Pav
    0.85
    rina
    0.83
     Dough
    0.81
     Sue
    0.80
    Activations Density 0.005%

    No Known Activations