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. 10376
    Prev
    Next
    INDEX
    Explanations

    terms related to interactive challenges or games like "trials," "puzzles," and "adventure."

    oai_token-act-pair · gpt-3.5-turbo

    elements related to gameplay mechanics in adventure and strategy games

    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
    inventoryQuantity
    -0.84
    catentry
    -0.76
    ocket
    -0.72
    paren
    -0.67
    lington
    -0.67
    dar
    -0.67
    ynt
    -0.67
    sounding
    -0.67
    issues
    -0.65
    minster
    -0.64
    POSITIVE LOGITS
     simulated
    0.95
     quiz
    0.84
     Simulator
    0.82
     simulation
    0.77
     proced
    0.77
     narrated
    0.77
     Encounter
    0.76
     simulations
    0.73
     multiplayer
    0.72
     randomized
    0.72
    Activations Density 0.866%

    No Known Activations