© 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. 9-ATT-KK
    11. 5500
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue and direct challenges in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.02
    2:0.04
    3:0.03
    4:0.04
    5:0.03
    6:0.29
    7:0.05
    8:0.07
    9:0.26
    10:0.02
    11:0.02
    Negative Logits
    Byte
    -3.96
     Byte
    -3.85
     Kodi
    -3.84
    akh
    -3.73
    tun
    -3.57
     Kul
    -3.48
     kb
    -3.40
     Fet
    -3.37
     Mb
    -3.34
     Hitch
    -3.27
    POSITIVE LOGITS
     Rose
    10.27
    Rose
    10.20
     Roses
    8.06
     roses
    7.67
    rose
    7.23
     rose
    5.84
    Ros
    4.87
     ROS
    4.82
     Ros
    4.62
     Rosa
    4.36
    Activations Density 0.010%

    No Known Activations