© 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. 12089
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and associated societal issues

    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
    0:0.02
    1:0.01
    2:0.02
    3:0.02
    4:0.03
    5:0.19
    6:0.02
    7:0.03
    8:0.01
    9:0.55
    10:0.02
    11:0.04
    Negative Logits
    ���
    -2.41
     itself
    -2.30
    rome
    -2.17
     contain
    -2.17
     accommodate
    -2.02
     resemble
    -2.02
     consisted
    -2.02
     coincided
    -2.02
     consist
    -1.94
     resembles
    -1.94
    POSITIVE LOGITS
    who
    5.68
     whom
    5.40
     who
    5.24
     whose
    4.12
    whose
    4.10
    Their
    3.49
     Who
    3.33
    their
    3.25
    WHO
    3.23
    Who
    3.19
    Activations Density 1.690%

    No Known Activations