© 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. 10-ATT-KK
    11. 23102
    Prev
    Next
    INDEX
    Explanations

    the presence and discussion of rare or unusual items and concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.07
    2:0.03
    3:0.05
    4:0.11
    5:0.03
    6:0.03
    7:0.35
    8:0.02
    9:0.08
    10:0.03
    11:0.11
    Negative Logits
     srfAttach
    -2.35
    Truth
    -2.26
     fals
    -2.23
     Crimes
    -2.04
     Truth
    -2.02
     Sonny
    -1.99
     Narc
    -1.97
     Boy
    -1.95
     Privacy
    -1.95
     Single
    -1.93
    POSITIVE LOGITS
    GMT
    2.70
     XD
    2.54
     Mew
    2.51
    tymology
    2.37
     Wem
    2.34
    ð
    2.33
    Pg
    2.31
     HDMI
    2.30
    daq
    2.29
    ��
    2.28
    Activations Density 0.013%

    No Known Activations