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. 7-RES-JB
    6. 19655
    Prev
    Next
    INDEX
    Explanations

    keywords related to video games, particularly titles like "Blizzard", "Hearthstone", and "World of Warcraft"

    oai_token-act-pair · gpt-3.5-turbo

    references to popular video game franchises and their associated titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incent
    -0.77
    asio
    -0.75
    achus
    -0.71
     pigeon
    -0.71
    ļéĨĴ
    -0.70
     glim
    -0.69
    yss
    -0.69
    aye
    -0.69
     embr
    -0.69
    ascript
    -0.68
    POSITIVE LOGITS
     Warcraft
    0.87
     Blizzard
    0.82
    Wiki
    0.82
     Entertainment
    0.80
    ORPG
    0.76
    RPG
    0.75
    Players
    0.74
    API
    0.73
     Wiki
    0.72
     Tournament
    0.70
    Activations Density 0.039%

    No Known Activations