© 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. 7085
    Prev
    Next
    INDEX
    Explanations

    ticketing and purchase information related to events

    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
    0:0.07
    1:0.03
    2:0.02
    3:0.06
    4:0.06
    5:0.03
    6:0.09
    7:0.37
    8:0.02
    9:0.03
    10:0.04
    11:0.14
    Negative Logits
     Tire
    -2.62
     bip
    -2.52
    Ray
    -2.51
     swords
    -2.43
    Torrent
    -2.40
     Beir
    -2.29
     Rapp
    -2.27
     Pars
    -2.24
     highways
    -2.22
     Erd
    -2.20
    POSITIVE LOGITS
    ieu
    2.46
    ogenic
    2.39
    acho
    2.36
    querade
    2.35
     VG
    2.29
    alg
    2.29
    uin
    2.28
     Cao
    2.26
    NK
    2.22
    ELF
    2.19
    Activations Density 0.018%

    No Known Activations