© 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. 17337
    Prev
    Next
    INDEX
    Explanations

    accounts of restoration efforts and their societal impacts

    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
    0:0.11
    1:0.14
    2:0.04
    3:0.21
    4:0.07
    5:0.02
    6:0.08
    7:0.11
    8:0.02
    9:0.04
    10:0.07
    11:0.05
    Negative Logits
    ILA
    -2.77
    thal
    -2.19
     {:
    -2.19
     Sof
    -2.12
     ≤
    -2.09
    Sing
    -2.04
    iu
    -2.03
    horn
    -2.00
     queer
    -1.96
     Que
    -1.95
    POSITIVE LOGITS
     restored
    5.80
     restoration
    5.69
     restore
    5.12
     restoring
    4.82
     resurrect
    4.69
     restores
    4.62
     rebuilt
    4.61
     revived
    4.57
     rebuilding
    4.53
     Restoration
    4.49
    Activations Density 0.073%

    No Known Activations