© 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. 9-ATT-KK
    11. 6633
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating quality or satisfaction in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.16
    1:0.02
    2:0.10
    3:0.22
    4:0.03
    5:0.05
    6:0.02
    7:0.05
    8:0.03
    9:0.01
    10:0.22
    11:0.02
    Negative Logits
     petitions
    -2.61
     Celebr
    -2.52
     crem
    -2.39
     petition
    -2.31
    Sources
    -2.23
     proclamation
    -2.17
     Citizenship
    -2.16
     spouses
    -2.12
     hashtag
    -2.09
     FedEx
    -2.08
    POSITIVE LOGITS
    cellent
    3.56
     flawless
    3.41
     superb
    3.27
     excellent
    3.05
     impecc
    2.94
    Excellent
    2.88
     marvelous
    2.86
    perfect
    2.81
     terrific
    2.79
     smooth
    2.76
    Activations Density 0.261%

    No Known Activations