© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15841
    Prev
    Next
    INDEX
    Explanations

    occurrences of key verbs and phrases related to the concept of understanding and desire in the context of improvement or progress

    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
    0:0.21
    1:0.09
    2:0.09
    3:0.05
    4:0.04
    5:0.04
    6:0.08
    7:0.07
    8:0.03
    9:0.06
    10:0.14
    11:0.07
    Negative Logits
     rim
    -3.34
     XY
    -3.30
     arom
    -3.19
    uminium
    -3.18
    Hu
    -3.11
    ══
    -3.08
     semin
    -3.02
     clay
    -3.00
    �
    -2.96
    IRC
    -2.95
    POSITIVE LOGITS
     Winn
    9.59
     Winnipeg
    5.33
     Gw
    4.28
     Manitoba
    4.19
     Wal
    4.09
     Wis
    4.08
     Kand
    3.86
     Willow
    3.79
     Wonderland
    3.79
     Po
    3.76
    Activations Density 0.000%

    No Known Activations