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. 3775
    Prev
    Next
    INDEX
    Explanations

    references to video games

    oai_token-act-pair · gpt-3.5-turbo

    mentions of games, specifically the word "Game" 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
    iewicz
    -0.77
     recip
    -0.75
    ophon
    -0.67
     commun
    -0.66
    yll
    -0.65
    Ó
    -0.65
    olson
    -0.64
     colle
    -0.64
    Marx
    -0.63
    inois
    -0.63
    POSITIVE LOGITS
     Game
    3.69
    Game
    2.91
     GAME
    2.50
    game
    2.14
    GAME
    2.05
     Games
    1.99
     game
    1.98
     games
    1.59
    games
    1.59
    Games
    1.58
    Activations Density 0.012%

    No Known Activations