© 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. 10765
    Prev
    Next
    INDEX
    Explanations

    connections between skills, knowledge, and professional experiences

    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
    1:0.04
    2:0.06
    3:0.04
    4:0.11
    5:0.02
    6:0.06
    7:0.37
    8:0.02
    9:0.04
    10:0.04
    11:0.11
    Negative Logits
     WiFi
    -2.41
    IFF
    -2.38
    EFF
    -2.24
     unlaw
    -2.21
    Cache
    -2.21
     Bluetooth
    -2.18
    ICE
    -2.16
    Skill
    -2.16
    achy
    -2.13
    ESH
    -2.13
    POSITIVE LOGITS
    atri
    2.57
     Villa
    2.41
     Pixar
    2.40
    azaki
    2.21
    icz
    2.20
    own
    2.13
     Uran
    2.13
     Ou
    2.12
     Moy
    2.12
     Planes
    2.07
    Activations Density 0.014%

    No Known Activations