© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 6885
    Prev
    Next
    INDEX
    Explanations

    dates and specific months in a document

    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
    0:0.03
    1:0.03
    2:0.08
    3:0.30
    4:0.11
    5:0.03
    6:0.03
    7:0.18
    8:0.07
    9:0.03
    10:0.03
    11:0.03
    Negative Logits
    UTC
    -2.65
    doms
    -2.45
     Edinburgh
    -2.38
    20439
    -2.37
    liv
    -2.30
     
    -2.28
     english
    -2.24
     Essex
    -2.23
    ð
    -2.21
     Scots
    -2.21
    POSITIVE LOGITS
    1983
    2.45
     Leopard
    2.42
    1984
    2.30
     Katz
    2.27
     1983
    2.27
     1969
    2.26
     1989
    2.25
     1973
    2.23
    使
    2.23
     1977
    2.22
    Activations Density 0.000%

    No Known Activations