© 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. 6555
    Prev
    Next
    INDEX
    Explanations

    geographic and contextual references linked to locations or demographics

    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
    0:0.03
    1:0.03
    2:0.05
    3:0.04
    4:0.07
    5:0.39
    6:0.03
    7:0.04
    8:0.02
    9:0.18
    10:0.03
    11:0.05
    Negative Logits
    theless
    -3.03
     forever
    -2.80
     indefinitely
    -2.69
     concurrently
    -2.59
    successfully
    -2.52
     JUST
    -2.49
     unlimited
    -2.43
    Then
    -2.36
     again
    -2.35
     another
    -2.35
    POSITIVE LOGITS
    where
    3.28
    when
    2.68
    particularly
    2.57
    */(
    2.56
    ocations
    2.55
    ogy
    2.52
    nant
    2.49
     when
    2.48
     where
    2.46
     (−
    2.34
    Activations Density 0.046%

    No Known Activations