© 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. 23119
    Prev
    Next
    INDEX
    Explanations

    references to a specific company or brand involved in a humorous context

    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
    0:0.13
    1:0.16
    2:0.05
    3:0.04
    4:0.05
    5:0.02
    6:0.05
    7:0.07
    8:0.04
    9:0.04
    10:0.25
    11:0.05
    Negative Logits
     Rath
    -3.49
    arding
    -3.37
     Rosenthal
    -3.35
    Mart
    -3.34
     inert
    -3.23
     Ryu
    -3.17
     Martha
    -3.12
    arf
    -3.06
     Samson
    -3.00
    Ram
    -2.98
    POSITIVE LOGITS
     Cre
    8.76
    Cre
    7.15
     cre
    6.84
    cre
    6.13
     Cr
    4.76
    CRE
    4.27
     CRE
    4.23
     Creep
    3.90
     Cro
    3.61
     Cle
    3.60
    Activations Density 0.002%

    No Known Activations