© 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. 5634
    Prev
    Next
    INDEX
    Explanations

    references to legal and official documents or proceedings

    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
    0:0.16
    1:0.01
    2:0.10
    3:0.05
    4:0.02
    5:0.06
    6:0.10
    7:0.04
    8:0.28
    9:0.09
    10:0.03
    11:0.01
    Negative Logits
    Xbox
    -3.56
     Wraith
    -3.48
     Angola
    -3.30
    Ireland
    -3.27
     Colts
    -3.24
     Gulf
    -3.23
    lua
    -3.20
     Foley
    -3.19
     Halo
    -3.14
     canoe
    -3.14
    POSITIVE LOGITS
     Berkeley
    9.13
    Ber
    6.35
     UC
    6.15
    keley
    5.70
     BART
    5.24
     Yiannopoulos
    5.12
     Oakland
    5.03
     Berk
    4.89
    UC
    4.67
     UCS
    4.66
    Activations Density 0.023%

    No Known Activations