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. 0-RES-JB
    6. 9273
    Prev
    Next
    INDEX
    Explanations

    references to sports games

    oai_token-act-pair · gpt-3.5-turbo

    mentions of games

    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
    wered
    -0.82
     Wilkinson
    -0.67
    Parameter
    -0.65
     Labrador
    -0.65
    iment
    -0.64
    Param
    -0.64
     Chevron
    -0.64
    posal
    -0.63
    upt
    -0.63
    ANGE
    -0.62
    POSITIVE LOGITS
     games
    3.51
    games
    2.83
     Games
    2.54
    Games
    2.50
     game
    2.19
    game
    2.02
    Game
    1.84
     tournaments
    1.84
     gaming
    1.81
     gamers
    1.77
    Activations Density 0.031%

    No Known Activations