© 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. 10614
    Prev
    Next
    INDEX
    Explanations

    expressions of discontent or resignation

    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
    0:0.20
    1:0.11
    2:0.06
    3:0.04
    4:0.05
    5:0.03
    6:0.08
    7:0.08
    8:0.01
    9:0.04
    10:0.17
    11:0.07
    Negative Logits
    anke
    -4.01
    Yan
    -3.96
     paras
    -3.73
    ayne
    -3.38
     Sabres
    -3.38
    ansas
    -3.22
    annis
    -3.16
    abwe
    -3.14
     UNC
    -3.13
    aida
    -3.07
    POSITIVE LOGITS
     Grind
    10.04
     grind
    6.56
     grinding
    5.30
     Tinder
    3.92
     churn
    3.68
     Gob
    3.59
     Lime
    3.48
     Bangalore
    3.45
     Grim
    3.44
     Crush
    3.40
    Activations Density 0.005%

    No Known Activations