© 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. 7667
    Prev
    Next
    INDEX
    Explanations

    references to reservation and what is included in bookings or arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.01
    1:0.02
    2:0.03
    3:0.05
    4:0.17
    5:0.03
    6:0.07
    7:0.37
    8:0.04
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
    enegger
    -1.84
    orer
    -1.70
    ibur
    -1.66
    atform
    -1.61
    ileaks
    -1.58
    agate
    -1.57
    akedown
    -1.53
    reprene
    -1.51
    wagen
    -1.49
    kefeller
    -1.46
    POSITIVE LOGITS
     discretion
    2.06
     reserve
    1.96
     reserves
    1.91
     scarce
    1.73
     precious
    1.71
     resources
    1.70
     veto
    1.66
     sparing
    1.65
     latitude
    1.56
     recourse
    1.49
    Activations Density 0.002%

    No Known Activations