© 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. 17158
    Prev
    Next
    INDEX
    Explanations

    references to various categories of products and features in commercial and digital contexts

    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
    0:0.03
    1:0.03
    2:0.04
    3:0.03
    4:0.05
    5:0.23
    6:0.03
    7:0.04
    8:0.02
    9:0.32
    10:0.03
    11:0.09
    Negative Logits
     expect
    -2.84
     ought
    -2.38
     rightfully
    -2.38
     rightly
    -2.32
     firsthand
    -2.32
     misunderstand
    -2.18
     expecting
    -2.14
     exhaustion
    -2.14
     surveyed
    -2.13
     comprehend
    -2.11
    POSITIVE LOGITS
    Adds
    2.81
    endum
    2.79
    �
    2.58
    added
    2.45
    Additional
    2.43
     thereto
    2.39
     Added
    2.39
     to
    2.38
    tones
    2.38
    onto
    2.36
    Activations Density 0.045%

    No Known Activations