© 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. 9500
    Prev
    Next
    INDEX
    Explanations

    information related to the Olympics such as athletes, events, and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the Olympics across different years and events

    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
     Ezra
    -0.85
     vape
    -0.79
     voic
    -0.76
     Reaper
    -0.76
    ebted
    -0.75
    Plugin
    -0.75
     cider
    -0.74
     Grayson
    -0.74
     DeV
    -0.74
     Tucker
    -0.72
    POSITIVE LOGITS
     IOC
    2.10
     Olympic
    2.05
     Olympics
    2.00
     Sochi
    1.90
     Athlet
    1.80
     Paraly
    1.75
     athletes
    1.74
     Olymp
    1.72
     Rio
    1.61
     medals
    1.59
    Activations Density 0.356%

    No Known Activations