© 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. 6507
    Prev
    Next
    INDEX
    Explanations

    instances of measurement or statistical performance metrics

    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
    0:0.06
    1:0.16
    2:0.04
    3:0.07
    4:0.05
    5:0.07
    6:0.13
    7:0.04
    8:0.03
    9:0.23
    10:0.04
    11:0.04
    Negative Logits
     TEXT
    -2.78
     rall
    -2.67
     Registered
    -2.64
    ////////
    -2.54
     BEL
    -2.51
     SOU
    -2.50
    -------------
    -2.49
     containment
    -2.48
     prol
    -2.48
    PLA
    -2.46
    POSITIVE LOGITS
     Hour
    3.80
    hour
    3.69
     Minute
    3.61
    Month
    3.56
    Hour
    3.56
    minute
    3.38
     Mile
    3.25
    peed
    3.21
    yard
    3.08
    minist
    2.98
    Activations Density 0.000%

    No Known Activations