© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 15375
    Prev
    Next
    INDEX
    Explanations

    references to characters and their interactions within a narrative, particularly focusing on the character Lady Susan

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.16
    1:0.11
    2:0.12
    3:0.04
    4:0.03
    5:0.03
    6:0.14
    7:0.10
    8:0.02
    9:0.05
    10:0.11
    11:0.03
    Negative Logits
     Paragu
    -3.15
     Kart
    -3.13
     Crypto
    -3.10
    rongh
    -3.09
     Spani
    -3.07
     pist
    -3.04
     Mata
    -2.95
     mould
    -2.92
     Jord
    -2.92
     Messi
    -2.90
    POSITIVE LOGITS
    Susan
    8.29
     Susan
    8.24
     Suzanne
    3.75
     Sue
    3.60
     Karen
    3.58
     Barbara
    3.31
    Sarah
    3.17
     Fay
    3.16
     Marilyn
    3.12
     Deborah
    3.12
    Activations Density 0.005%

    No Known Activations