© 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. 8922
    Prev
    Next
    INDEX
    Explanations

    self-referential expressions and notions of self-respect in a literary context

    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
    1:0.06
    2:0.06
    3:0.07
    4:0.06
    5:0.03
    6:0.07
    7:0.14
    8:0.05
    9:0.05
    10:0.09
    11:0.06
    Negative Logits
     UAE
    -3.16
     Mub
    -3.02
     Bahrain
    -2.95
     Dubai
    -2.90
     Bulls
    -2.73
     CF
    -2.71
    munition
    -2.68
    Saudi
    -2.63
     BlackBerry
    -2.62
     Garmin
    -2.59
    POSITIVE LOGITS
     Lovecraft
    7.59
     Cthulhu
    6.77
    ulhu
    4.49
     Cth
    4.46
     Conan
    4.22
     Carpenter
    3.76
     Gothic
    3.63
     Nec
    3.53
     Warp
    3.38
     eld
    3.29
    Activations Density 0.001%

    No Known Activations