© 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. 5544
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to events or outcomes

    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
    1:0.03
    2:0.04
    3:0.10
    4:0.02
    5:0.06
    6:0.26
    7:0.05
    8:0.03
    9:0.17
    10:0.05
    11:0.09
    Negative Logits
     Cole
    -3.22
     CODE
    -3.10
     stairs
    -3.08
     Everett
    -3.01
     Erit
    -2.97
     elevator
    -2.93
     Engineers
    -2.88
     ELE
    -2.85
     staircase
    -2.83
     ceiling
    -2.77
    POSITIVE LOGITS
    oval
    3.05
    urer
    2.91
    elfare
    2.84
    berman
    2.77
    arching
    2.71
    ounty
    2.67
    ighth
    2.66
    69
    2.65
    ateur
    2.64
    oil
    2.63
    Activations Density 0.010%

    No Known Activations