© 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. 11369
    Prev
    Next
    INDEX
    Explanations

    the word "Quinn"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Quinn" as well as its variants in various contexts

    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
     dehyd
    -0.72
     eat
    -0.69
    Fuel
    -0.68
     py
    -0.67
     heating
    -0.67
    Food
    -0.67
     meal
    -0.66
     ate
    -0.65
     malt
    -0.64
     ascent
    -0.64
    POSITIVE LOGITS
     Quinn
    4.27
     Quin
    1.62
     Zoe
    1.24
     Grayson
    1.23
     Shanahan
    1.21
     Rasmussen
    1.21
     Brennan
    1.20
     Quan
    1.18
     Whitman
    1.13
     Garr
    1.13
    Activations Density 0.024%

    No Known Activations