© 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. 17251
    Prev
    Next
    INDEX
    Explanations

    discussions on the movement and treatment of transgender prisoners

    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
    0:0.10
    1:0.20
    2:0.06
    3:0.03
    4:0.04
    5:0.02
    6:0.07
    7:0.09
    8:0.02
    9:0.04
    10:0.20
    11:0.06
    Negative Logits
    ministic
    -2.86
     Ty
    -2.71
    Ty
    -2.69
     symm
    -2.56
     Quantum
    -2.52
    Ky
    -2.46
     Sync
    -2.45
     NRS
    -2.42
     NX
    -2.41
     entangled
    -2.37
    POSITIVE LOGITS
     Fol
    8.34
     fol
    5.20
    fol
    4.96
     Ful
    4.20
     Dol
    3.83
     Fur
    3.78
     Bel
    3.42
     Folk
    3.41
     Pul
    3.38
     Bol
    3.36
    Activations Density 0.002%

    No Known Activations