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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43865
    Prev
    Next
    INDEX
    Explanations

    references to deck-building mechanics in card games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.03
    3:0.07
    4:0.04
    5:0.04
    6:0.02
    7:0.04
    8:0.02
    9:0.09
    10:0.40
    11:0.15
    Negative Logits
     answ
    -1.42
     deaf
    -1.40
     seism
    -1.37
    talk
    -1.37
     CCTV
    -1.37
     whistlebl
    -1.36
     whistleblowers
    -1.34
     Hearing
    -1.34
     DMCA
    -1.33
     screenings
    -1.32
    POSITIVE LOGITS
    ixture
    1.38
    erker
    1.36
    atta
    1.33
    pure
    1.32
     cruc
    1.29
    ophy
    1.27
     hybrid
    1.27
     repertoire
    1.26
     variants
    1.26
    inav
    1.25
    Activations Density 0.059%

    No Known Activations