© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 22095
    Prev
    Next
    INDEX
    Explanations

    mentions of the Olympics and related terms like gold medalist

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Olympic events and athletes

    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
    iri
    -0.74
    othal
    -0.72
    arily
    -0.71
    arial
    -0.70
    ouri
    -0.69
    rences
    -0.68
    stocks
    -0.66
    drawn
    -0.66
    vironment
    -0.64
    eric
    -0.64
    POSITIVE LOGITS
     medal
    1.13
     medals
    1.06
     Games
    0.97
    lymp
    0.96
     Torch
    0.96
     Medal
    0.95
     torch
    0.94
     Athlet
    0.94
     athletes
    0.90
     Trials
    0.90
    Activations Density 0.050%

    No Known Activations