Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 17324
    Prev
    Next
    INDEX
    Explanations

    phrases related to the video game "League of Legends"

    oai_token-act-pair · gpt-3.5-turbo

    references to the video game "League of Legends."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rollout
    -0.67
    jee
    -0.65
    detail
    -0.63
    nyder
    -0.62
     Nieto
    -0.61
     inaction
    -0.61
     warranties
    -0.61
    steen
    -0.60
    OPLE
    -0.59
     cellul
    -0.59
    POSITIVE LOGITS
     Legends
    0.85
     Zelda
    0.75
     Esports
    0.68
    ansom
    0.67
     Rhythm
    0.66
    utters
    0.66
    Arcade
    0.66
     Gaming
    0.66
    ighters
    0.65
    ookie
    0.64
    Activations Density 0.072%

    No Known Activations