© 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. 22638
    Prev
    Next
    INDEX
    Explanations

    phrases related to analysis and evaluation of narratives or texts

    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
    0:0.20
    1:0.07
    2:0.06
    3:0.04
    4:0.04
    5:0.02
    6:0.10
    7:0.11
    8:0.01
    9:0.04
    10:0.21
    11:0.05
    Negative Logits
    geist
    -3.04
     SPD
    -3.04
    ICES
    -3.03
    urches
    -2.86
     FG
    -2.79
     DM
    -2.79
    AMD
    -2.73
    ertodd
    -2.63
    ottesville
    -2.62
     GP
    -2.60
    POSITIVE LOGITS
     Nab
    9.86
     Zub
    4.88
     Neb
    4.78
     Lol
    4.22
     Bab
    4.04
     Rab
    3.95
     Tat
    3.86
     Nim
    3.73
     Kazakh
    3.72
     Jab
    3.69
    Activations Density 0.002%

    No Known Activations