© 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. 5766
    Prev
    Next
    INDEX
    Explanations

    pronouns or referential words indicating a subject or object

    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
    0:0.08
    1:0.08
    2:0.08
    3:0.07
    4:0.08
    5:0.09
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.07
    11:0.07
    Negative Logits
     apost
    -3.93
     ordinances
    -3.41
     citations
    -3.14
     Apost
    -3.03
     abbrevi
    -3.01
     affili
    -2.92
     Fas
    -2.90
     geography
    -2.90
     strongh
    -2.88
     pronouns
    -2.82
    POSITIVE LOGITS
    lav
    3.02
    gio
    2.99
    wart
    2.86
    gallery
    2.81
    wine
    2.81
     champagne
    2.81
    raz
    2.75
    posal
    2.73
    jandro
    2.73
    lain
    2.71
    Activations Density 0.000%

    No Known Activations