© 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. 11893
    Prev
    Next
    INDEX
    Explanations

    quantifiable metrics related to industry, financial performance, and production capacity

    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
    0:0.02
    1:0.02
    2:0.03
    3:0.02
    4:0.05
    5:0.38
    6:0.02
    7:0.03
    8:0.01
    9:0.30
    10:0.01
    11:0.05
    Negative Logits
    pired
    -2.50
     hadn
    -2.39
    ディ
    -2.31
     ought
    -2.29
    urn
    -2.23
     existed
    -2.23
    bent
    -2.23
     behaved
    -2.23
    iar
    -2.14
    版
    -2.12
    POSITIVE LOGITS
     by
    4.29
     considerably
    4.09
    By
    3.70
     tremendously
    3.63
     significantly
    3.55
    by
    3.52
     By
    3.34
     dramatically
    3.18
     substantially
    3.15
     drastically
    3.13
    Activations Density 0.404%

    No Known Activations