© 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. 5-ATT-KK
    11. 10175
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, particularly related to locations and entities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.07
    3:0.04
    4:0.06
    5:0.03
    6:0.33
    7:0.04
    8:0.04
    9:0.04
    10:0.11
    11:0.13
    Negative Logits
    imester
    -1.47
     Scully
    -1.23
     Sloan
    -1.20
    advertisement
    -1.18
    κ
    -1.16
    lift
    -1.14
    restrial
    -1.09
     Nolan
    -1.09
     onboard
    -1.09
    ּ
    -1.07
    POSITIVE LOGITS
    uru
    1.38
    artifacts
    1.36
    achu
    1.31
     Tid
    1.31
    atta
    1.24
    asus
    1.23
    rouse
    1.20
     Sounds
    1.19
    BUG
    1.19
    aukee
    1.18
    Activations Density 0.007%

    No Known Activations