© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 16735
    Prev
    Next
    INDEX
    Explanations

    references to various units and locations in a structured setting, possibly pertaining to series and player-related data

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.22
    1:0.17
    2:0.03
    3:0.03
    4:0.02
    5:0.22
    6:0.03
    7:0.02
    8:0.10
    9:0.05
    10:0.04
    11:0.03
    Negative Logits
    panic
    -2.09
    asper
    -2.01
    externalActionCode
    -1.95
    raised
    -1.91
    bats
    -1.84
    abre
    -1.83
    itiz
    -1.79
    zbollah
    -1.76
    roleum
    -1.75
    Pokémon
    -1.67
    POSITIVE LOGITS
     Closed
    1.90
     1
    1.81
     TBD
    1.69
     2
    1.63
     01
    1.52
     3
    1.51
     NCT
    1.51
     0
    1.50
     18
    1.50
     Doe
    1.47
    Activations Density 0.020%

    No Known Activations