© 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. 12698
    Prev
    Next
    INDEX
    Explanations

    numerical and class-related information, particularly focusing on statistics or figures related to projects or plans

    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
    0:0.11
    1:0.05
    2:0.11
    3:0.03
    4:0.02
    5:0.02
    6:0.23
    7:0.10
    8:0.03
    9:0.03
    10:0.17
    11:0.03
    Negative Logits
     Ze
    -2.75
     Orth
    -2.73
     Dunk
    -2.69
     Palm
    -2.66
     Ezekiel
    -2.60
    bos
    -2.60
    ザ
    -2.56
     Stra
    -2.54
    snap
    -2.54
     therap
    -2.52
    POSITIVE LOGITS
     CC
    8.86
    CC
    8.27
     cc
    6.56
    CCC
    6.09
    cc
    5.55
    DC
    4.52
     CCP
    4.47
     TC
    4.35
     BCC
    4.34
    AC
    4.26
    Activations Density 0.006%

    No Known Activations