© 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. 10-ATT-KK
    11. 17176
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.08
    1:0.13
    2:0.10
    3:0.09
    4:0.06
    5:0.03
    6:0.07
    7:0.13
    8:0.05
    9:0.05
    10:0.12
    11:0.04
    Negative Logits
    BRE
    -2.49
     React
    -2.34
    vez
    -2.28
    oric
    -2.27
     �
    -2.25
    ‎
    -2.21
     Breaker
    -2.21
     ―
    -2.19
     Rat
    -2.18
    �
    -2.17
    POSITIVE LOGITS
    retty
    3.40
    Unix
    2.72
     サーティワン
    2.68
    natureconservancy
    2.63
     Bangalore
    2.58
    ThumbnailImage
    2.54
    senal
    2.50
    culosis
    2.49
     神
    2.48
    ailability
    2.43
    Activations Density 0.000%

    No Known Activations