© 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. 39637
    Prev
    Next
    INDEX
    Explanations

    numerical data related to age, time, and quantities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.27
    3:0.16
    4:0.07
    5:0.05
    6:0.04
    7:0.04
    8:0.06
    9:0.10
    10:0.08
    11:0.05
    Negative Logits
     dissu
    -1.33
     discour
    -1.32
    onite
    -1.31
     whereas
    -1.30
     footh
    -1.29
    orsi
    -1.27
    ña
    -1.23
    tern
    -1.20
    hesda
    -1.20
    ğ
    -1.20
    POSITIVE LOGITS
    将
    1.83
    ゴン
    1.70
    ベ
    1.54
    は
    1.52
    作
    1.45
    ンジ
    1.43
    ��
    1.43
    ワン
    1.42
    版
    1.42
    ギ
    1.39
    Activations Density 0.041%

    No Known Activations