© 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. 23295
    Prev
    Next
    INDEX
    Explanations

    themes related to pain, suffering, and existential questions

    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
    0:0.07
    1:0.02
    2:0.04
    3:0.04
    4:0.16
    5:0.02
    6:0.03
    7:0.40
    8:0.01
    9:0.02
    10:0.02
    11:0.12
    Negative Logits
    gil
    -2.82
    akespe
    -2.40
    inances
    -2.39
     Poker
    -2.33
    pole
    -2.31
     Beer
    -2.25
     Prayer
    -2.25
    pee
    -2.22
     Poke
    -2.19
    �
    -2.19
    POSITIVE LOGITS
    ussen
    2.56
     Stern
    2.48
     Kraft
    2.46
     Kazakh
    2.45
     Sinn
    2.33
    NN
    2.32
    ISION
    2.22
     UA
    2.22
    SN
    2.21
     Goddard
    2.18
    Activations Density 0.012%

    No Known Activations