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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 16784
    Prev
    Next
    INDEX
    Explanations

    concepts related to a deck like in card games or a physical structure

    oai_token-act-pair · gpt-3.5-turbo

    references to decks of cards or game elements related to card games

    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
    çīĪ
    -0.94
    heric
    -0.87
    alez
    -0.71
    ipient
    -0.67
     Griffith
    -0.67
    ternity
    -0.66
    avez
    -0.65
    atell
    -0.64
    entity
    -0.64
    ankind
    -0.62
    POSITIVE LOGITS
     deck
    1.29
     decks
    1.25
     Deck
    1.18
    deck
    1.17
    wright
    1.03
    lists
    1.01
    board
    0.97
    igans
    0.94
    mates
    0.92
    yard
    0.89
    Activations Density 0.009%

    No Known Activations