© 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. 15042
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive forms indicating relationships and emotional connections

    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
    0:0.09
    1:0.09
    2:0.08
    3:0.05
    4:0.07
    5:0.03
    6:0.10
    7:0.22
    8:0.02
    9:0.04
    10:0.05
    11:0.11
    Negative Logits
     Juda
    -2.54
    inka
    -2.34
     Medals
    -2.26
     Yad
    -2.10
     Audit
    -1.99
     Parables
    -1.99
    Management
    -1.97
     pilgrims
    -1.97
    Aid
    -1.94
     ADA
    -1.93
    POSITIVE LOGITS
     boyfriend
    3.04
    esome
    2.54
    hook
    2.35
     Tinder
    2.28
     girlfriend
    2.28
    girlfriend
    2.22
     hook
    2.15
     monog
    2.12
     Fren
    2.09
     cheating
    2.02
    Activations Density 0.004%

    No Known Activations