© 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. 0-RES-JB
    11. 8224
    Prev
    Next
    INDEX
    Explanations

    references to the name "Katy."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Katy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exile
    -0.83
     moss
    -0.77
     Rhino
    -0.77
    cius
    -0.76
     guards
    -0.75
    Rot
    -0.73
     guard
    -0.70
    ROM
    -0.70
    olin
    -0.69
    otine
    -0.69
    POSITIVE LOGITS
     Katy
    3.78
     Katie
    2.31
    Kat
    2.16
    kat
    1.47
     Katrina
    1.25
     Katz
    1.21
     Rih
    1.16
     Kara
    1.16
     KP
    1.16
     Beyon
    1.12
    Activations Density 0.033%

    No Known Activations