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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 19274
    Prev
    Next
    INDEX
    Explanations

    information related to a specific game or fictional universe with terms such as "Shard," "Exotic Shards," and actions like "obtained," "purchased," and "upgrade."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to game mechanics and item acquisition

    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
     Zika
    -0.77
    Georg
    -0.76
     Vaughan
    -0.75
     Georg
    -0.74
     Horton
    -0.74
    AIDS
    -0.73
     Kaufman
    -0.70
     ADHD
    -0.70
    LIN
    -0.69
    amera
    -0.69
    POSITIVE LOGITS
     Crafting
    1.48
     crafting
    1.45
     Shards
    1.32
     gems
    1.28
     rarity
    1.27
     enchant
    1.26
     loot
    1.26
     enchanted
    1.25
     potions
    1.22
     crafted
    1.22
    Activations Density 0.296%

    No Known Activations