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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 6572
    Prev
    Next
    INDEX
    Explanations

    terminology related to the video game "StarCraft."

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to competitive gaming, particularly in StarCraft

    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
    trak
    -0.73
    bury
    -0.72
    arettes
    -0.68
    20439
    -0.66
    andro
    -0.66
    jury
    -0.65
    yss
    -0.65
    ewitness
    -0.65
    awaru
    -0.65
    代
    -0.65
    POSITIVE LOGITS
     StarCraft
    1.13
     Starcraft
    1.03
     Zerg
    0.96
     Protoss
    0.90
    lords
    0.82
     GSL
    0.80
     Terran
    0.77
     BW
    0.76
     Swarm
    0.74
    craft
    0.71
    Activations Density 0.023%

    No Known Activations