© 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. 6338
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and quantities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.04
    1:0.15
    2:0.03
    3:0.07
    4:0.01
    5:0.03
    6:0.15
    7:0.02
    8:0.03
    9:0.34
    10:0.02
    11:0.03
    Negative Logits
     Cron
    -3.98
    UC
    -3.52
    CCC
    -3.44
    ================
    -3.41
    CC
    -3.38
     1994
    -3.27
     Schwar
    -3.25
     Lub
    -3.24
     Blumenthal
    -3.23
    SC
    -3.22
    POSITIVE LOGITS
    way
    5.24
    WAY
    5.06
    Way
    4.71
    ways
    4.32
     Way
    3.92
    eway
    3.59
     Howe
    3.49
     Wick
    3.41
     WAY
    3.38
     roadway
    3.36
    Activations Density 0.001%

    No Known Activations