© 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. 23156
    Prev
    Next
    INDEX
    Explanations

    indications of examples or instances of something being discussed

    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
    0:0.08
    1:0.02
    2:0.09
    3:0.10
    4:0.11
    5:0.06
    6:0.02
    7:0.08
    8:0.03
    9:0.21
    10:0.03
    11:0.11
    Negative Logits
     externalToEVAOnly
    -2.35
    ustomed
    -2.26
    amed
    -2.12
     cob
    -2.10
    aughs
    -2.08
     ejected
    -2.07
    udeb
    -2.06
    asy
    -2.00
    JUST
    -1.98
    IED
    -1.96
    POSITIVE LOGITS
    �
    4.80
     �
    3.87
    ibaba
    3.22
     │
    3.20
     �
    3.15
    �
    3.07
    �
    2.81
    ̶
    2.75
     illust
    2.50
     ›
    2.50
    Activations Density 0.017%

    No Known Activations