© 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. 6572
    Prev
    Next
    INDEX
    Explanations

    the conjunction "or" and the adverb "as."

    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
    1:0.07
    2:0.09
    3:0.09
    4:0.07
    5:0.08
    6:0.07
    7:0.07
    8:0.08
    9:0.09
    10:0.09
    11:0.07
    Negative Logits
     Cust
    -3.14
    etsk
    -2.96
    [_
    -2.90
    wcs
    -2.80
    uminati
    -2.76
    [/
    -2.74
    Sov
    -2.72
    plom
    -2.72
    Shares
    -2.71
    UTERS
    -2.61
    POSITIVE LOGITS
     Greenwood
    2.99
     perfume
    2.80
     spiked
    2.48
     fragrance
    2.40
     sampled
    2.39
     Broadway
    2.31
     Bicycle
    2.31
     Tropical
    2.30
     Beach
    2.28
     seafood
    2.28
    Activations Density 0.000%

    No Known Activations