© 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. 23249
    Prev
    Next
    INDEX
    Explanations

    punctuation and structured text elements in sentences

    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
    0:0.17
    1:0.06
    2:0.08
    3:0.13
    4:0.06
    5:0.03
    6:0.08
    7:0.07
    8:0.04
    9:0.07
    10:0.10
    11:0.07
    Negative Logits
     Carlson
    -3.59
    poke
    -2.85
     Cohn
    -2.85
    ski
    -2.84
    rador
    -2.67
    Ice
    -2.65
    cius
    -2.58
    ove
    -2.52
    olphin
    -2.51
    inders
    -2.50
    POSITIVE LOGITS
     Baghdad
    4.50
     Jihad
    4.47
     Palestin
    4.39
     Fall
    4.32
    ujah
    4.31
     Abu
    4.00
     Shia
    3.92
     Abbas
    3.90
     Palestine
    3.86
     Rash
    3.77
    Activations Density 0.001%

    No Known Activations