© 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. 10593
    Prev
    Next
    INDEX
    Explanations

    phrases and references to legal and formal agreements or decisions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.03
    3:0.02
    4:0.05
    5:0.19
    6:0.01
    7:0.02
    8:0.01
    9:0.56
    10:0.00
    11:0.03
    Negative Logits
    Recomm
    -2.45
     Learns
    -2.30
    mits
    -2.22
     thinks
    -2.22
     Gets
    -2.16
     Talks
    -2.12
    orses
    -2.11
    pires
    -2.08
     believes
    -2.05
     Says
    -2.04
    POSITIVE LOGITS
     are
    4.91
     aren
    4.62
     remain
    4.20
     constitute
    4.14
     comprise
    4.13
     appear
    4.08
     occur
    3.98
     were
    3.98
     differ
    3.96
     arise
    3.94
    Activations Density 2.826%

    No Known Activations