© 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. 24804
    Prev
    Next
    INDEX
    Explanations

    phrases related to adaptation and change

    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
    0:0.01
    1:0.02
    2:0.09
    3:0.08
    4:0.38
    5:0.05
    6:0.03
    7:0.13
    8:0.02
    9:0.04
    10:0.04
    11:0.05
    Negative Logits
    Balt
    -1.93
    externalActionCode
    -1.70
    owned
    -1.61
    lishes
    -1.57
    ridor
    -1.56
    Registered
    -1.53
    oola
    -1.52
    iliated
    -1.50
    �
    -1.49
    osponsors
    -1.49
    POSITIVE LOGITS
     antics
    2.16
     advances
    1.94
     offerings
    1.94
    eness
    1.86
     lack
    1.83
     impending
    1.77
     nuances
    1.77
     developments
    1.76
     encro
    1.75
     injust
    1.74
    Activations Density 0.421%

    No Known Activations