© 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. 43684
    Prev
    Next
    INDEX
    Explanations

    instances of "back and forth" interactions or exchanges

    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
    1:0.00
    2:0.12
    3:0.05
    4:0.09
    5:0.02
    6:0.03
    7:0.39
    8:0.04
    9:0.03
    10:0.11
    11:0.04
    Negative Logits
     Cure
    -1.96
     Thief
    -1.70
     Lucky
    -1.68
     Nurse
    -1.62
     Courage
    -1.62
    ainted
    -1.62
     Accessories
    -1.61
     Preservation
    -1.56
     Survivors
    -1.55
     Ribbon
    -1.55
    POSITIVE LOGITS
     scrimmage
    1.95
     topics
    1.85
    appro
    1.77
     transact
    1.77
     conflicting
    1.76
     between
    1.76
     transactions
    1.75
     motions
    1.75
     aisle
    1.74
     negotiation
    1.71
    Activations Density 0.002%

    No Known Activations