© 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. 10870
    Prev
    Next
    INDEX
    Explanations

    text related to organizational and policy issues, particularly concerning institutional actions or accountability

    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
    0:0.05
    1:0.02
    2:0.03
    3:0.05
    4:0.31
    5:0.02
    6:0.10
    7:0.07
    8:0.12
    9:0.08
    10:0.08
    11:0.02
    Negative Logits
     Flavoring
    -2.38
     (?,
    -2.33
     Extras
    -2.31
     Sturgeon
    -2.16
    aceae
    -2.13
     Masquerade
    -2.11
     guiName
    -2.09
     Shades
    -2.09
     Sins
    -2.04
     accommod
    -1.99
    POSITIVE LOGITS
    SIGN
    2.60
    orse
    2.38
    Missing
    2.33
    �
    2.30
    KC
    2.28
    ancock
    2.18
    email
    2.15
    faith
    2.14
    DN
    2.10
    WT
    2.10
    Activations Density 0.001%

    No Known Activations