© 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. 16731
    Prev
    Next
    INDEX
    Explanations

    language that emphasizes how to categorize or group specific entities

    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
    0:0.03
    1:0.02
    2:0.05
    3:0.06
    4:0.39
    5:0.03
    6:0.10
    7:0.07
    8:0.03
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
     promotion
    -1.53
    ��
    -1.51
    GD
    -1.47
     裏�
    -1.45
    AGES
    -1.43
     redemption
    -1.41
    zsche
    -1.41
     rebounds
    -1.40
     Reach
    -1.40
     transc
    -1.37
    POSITIVE LOGITS
    aneously
    1.81
     snug
    1.78
    arse
    1.75
    neutral
    1.69
    eper
    1.66
    ationally
    1.64
     asleep
    1.64
    vantage
    1.60
    square
    1.58
    ishly
    1.56
    Activations Density 0.027%

    No Known Activations