Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 13581
    Prev
    Next
    INDEX
    Explanations

    references to the Olympic Games

    oai_token-act-pair · gpt-3.5-turbo

    references to the Olympic Games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...]
    -0.78
    utils
    -0.71
    lessly
    -0.70
    cha
    -0.69
    hra
    -0.68
    drawn
    -0.68
    vironment
    -0.67
    finding
    -0.64
    BOOK
    -0.62
    flies
    -0.61
    POSITIVE LOGITS
     Olympic
    1.13
     athletes
    0.94
     athlete
    0.93
     Athlet
    0.91
     gymn
    0.87
     IOC
    0.86
     Olympics
    0.86
     Torch
    0.84
    bledon
    0.83
     Olymp
    0.78
    Activations Density 0.005%

    No Known Activations