© 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. 10619
    Prev
    Next
    INDEX
    Explanations

    concepts related to societal issues and support for organizations

    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
    0:0.03
    1:0.02
    2:0.04
    3:0.04
    4:0.07
    5:0.47
    6:0.02
    7:0.03
    8:0.03
    9:0.14
    10:0.02
    11:0.03
    Negative Logits
     anymore
    -4.29
     again
    -4.06
     now
    -3.50
     indicated
    -3.39
     normally
    -3.25
     currently
    -3.17
     hadn
    -3.17
     if
    -3.06
     once
    -3.03
     still
    -3.02
    POSITIVE LOGITS
    than
    3.52
    ソ
    2.90
    ヤ
    2.72
    prise
    2.60
    �
    2.59
    ventus
    2.58
    iannopoulos
    2.52
    ":[{"
    2.52
    ディ
    2.50
    plet
    2.44
    Activations Density 0.098%

    No Known Activations