© 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. 9-ATT-KK
    11. 5587
    Prev
    Next
    INDEX
    Explanations

    references to discussions or mentions of various topics, particularly related to events or matters under investigation

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.06
    1:0.04
    2:0.05
    3:0.06
    4:0.04
    5:0.05
    6:0.24
    7:0.06
    8:0.05
    9:0.24
    10:0.02
    11:0.03
    Negative Logits
    ヘラ
    -4.01
    サ
    -3.92
     Pulse
    -3.72
     Modes
    -3.72
    otor
    -3.54
     Pix
    -3.51
    chanted
    -3.43
     index
    -3.42
     Orlando
    -3.38
    ItemTracker
    -3.32
    POSITIVE LOGITS
    Ger
    8.87
     Ger
    8.73
     ger
    7.56
     GER
    6.47
    ger
    5.63
     Germ
    5.36
    GER
    5.25
     germ
    5.23
     Berger
    4.65
     glacier
    4.47
    Activations Density 0.001%

    No Known Activations