© 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. 6497
    Prev
    Next
    INDEX
    Explanations

    specific timestamps or time indicators in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.03
    1:0.23
    2:0.03
    3:0.05
    4:0.04
    5:0.08
    6:0.02
    7:0.10
    8:0.03
    9:0.09
    10:0.16
    11:0.08
    Negative Logits
    yle
    -2.57
     Straw
    -2.54
     Sz
    -2.41
     Hawkins
    -2.33
     Sutherland
    -2.30
    allo
    -2.19
     whit
    -2.19
     reorgan
    -2.16
    ortium
    -2.12
     tuple
    -2.11
    POSITIVE LOGITS
     GMT
    3.73
    GMT
    3.35
     mast
    2.53
    omb
    2.50
    Associated
    2.46
    IM
    2.45
    auts
    2.43
    CHAT
    2.38
    AMP
    2.36
    AMA
    2.31
    Activations Density 0.000%

    No Known Activations