© 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. 9-ATT-KK
    11. 6320
    Prev
    Next
    INDEX
    Explanations

    terms related to inheritance and taxation

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.12
    1:0.03
    2:0.26
    3:0.10
    4:0.03
    5:0.12
    6:0.04
    7:0.07
    8:0.06
    9:0.02
    10:0.06
    11:0.04
    Negative Logits
    english
    -2.68
     captcha
    -2.56
     fatigue
    -2.55
     blackout
    -2.48
    ophobia
    -2.47
     Transit
    -2.47
     lockout
    -2.44
    blocking
    -2.43
     blocker
    -2.42
    ggle
    -2.39
    POSITIVE LOGITS
     heirs
    4.95
     estates
    4.72
    estate
    4.40
     estate
    4.33
     inheritance
    4.14
     Estate
    4.11
     inherit
    4.07
     widow
    3.99
     execut
    3.67
     crem
    3.53
    Activations Density 0.002%

    No Known Activations