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. 3-RES-JB
    6. 7499
    Prev
    Next
    INDEX
    Explanations

    references to building or customizing decks for a game or cards

    oai_token-act-pair · gpt-3.5-turbo

    references to "deck" in the context of card games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.86
    heric
    -0.77
    ternity
    -0.74
    ipient
    -0.70
    phrine
    -0.67
    alez
    -0.65
    pheus
    -0.64
     Geneva
    -0.63
    atos
    -0.61
    entity
    -0.60
    POSITIVE LOGITS
    lists
    1.14
     deck
    1.09
     decks
    1.03
    igans
    0.95
     Deck
    0.95
    deck
    0.94
    list
    0.94
    wright
    0.93
    igan
    0.92
    mates
    0.88
    Activations Density 0.017%

    No Known Activations