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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18786
    Prev
    Next
    INDEX
    Explanations

    references to tabletop role-playing games, specifically focusing on the mechanics and settings related to Dungeons & Dragons and similar systems

    oai_token-act-pair · gpt-3.5-turbo

    references to role-playing games and their elements

    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
     Simmons
    -0.95
     Kenny
    -0.89
     Rodrig
    -0.87
     Kendrick
    -0.81
     Cabrera
    -0.79
    amsung
    -0.79
    aspers
    -0.79
    inventoryQuantity
    -0.78
     Gutierrez
    -0.77
    peat
    -0.74
    POSITIVE LOGITS
     Dungeons
    1.82
     Pathfinder
    1.71
     Warhammer
    1.66
     tabletop
    1.63
     Cthulhu
    1.55
     Dungeon
    1.54
     RPGs
    1.49
     Realms
    1.49
    RPG
    1.48
     Wizards
    1.46
    Activations Density 0.397%

    No Known Activations