© 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. 30230
    Prev
    Next
    INDEX
    Explanations

    instances of emphasis on suffering and its visibility in specific contexts

    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
    2:0.17
    3:0.23
    4:0.13
    5:0.03
    6:0.05
    7:0.08
    8:0.04
    9:0.04
    10:0.04
    11:0.08
    Negative Logits
     deserves
    -2.01
     deserve
    -1.85
     blah
    -1.65
     someday
    -1.63
     accordingly
    -1.52
     shouldn
    -1.51
     FOIA
    -1.50
     fab
    -1.44
     owe
    -1.42
     tyr
    -1.40
    POSITIVE LOGITS
    occupied
    1.62
    phe
    1.62
    ]:
    1.55
    lied
    1.54
     Hamm
    1.54
    angled
    1.53
    rous
    1.46
    SPONSORED
    1.46
    "],
    1.44
     Musk
    1.43
    Activations Density 0.000%

    No Known Activations