© 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. 5537
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and contact information

    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
    0:0.09
    1:0.02
    2:0.07
    3:0.07
    4:0.14
    5:0.09
    6:0.03
    7:0.19
    8:0.08
    9:0.02
    10:0.10
    11:0.05
    Negative Logits
    bidden
    -2.23
    urious
    -2.15
     Heist
    -2.14
    sequently
    -2.11
     disbel
    -2.07
     unsurprisingly
    -1.99
     hindsight
    -1.98
    umers
    -1.97
     decisively
    -1.96
    later
    -1.94
    POSITIVE LOGITS
    Copyright
    2.63
    20439
    2.59
     Email
    2.48
    Fax
    2.47
    ullivan
    2.47
     Print
    2.47
    Contact
    2.43
     Cosponsors
    2.37
     fax
    2.36
     mail
    2.29
    Activations Density 0.027%

    No Known Activations