© 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. 19992
    Prev
    Next
    INDEX
    Explanations

    geographic locations and names of states or regions

    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
    0:0.05
    1:0.11
    2:0.04
    3:0.05
    4:0.04
    5:0.05
    6:0.13
    7:0.21
    8:0.04
    9:0.03
    10:0.14
    11:0.05
    Negative Logits
     FTC
    -2.27
     iT
    -2.01
     TM
    -1.98
     Mell
    -1.97
    Bloomberg
    -1.93
     NBN
    -1.92
    Iv
    -1.92
     Hath
    -1.89
     jurisdictions
    -1.88
     Punjab
    -1.88
    POSITIVE LOGITS
    anova
    2.52
     Cal
    2.22
     Graduate
    2.17
    chance
    2.16
     freshmen
    2.15
    angelo
    2.15
     Gau
    2.14
    wu
    2.14
    sch
    2.10
    SU
    2.08
    Activations Density 0.004%

    No Known Activations