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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14903
    Prev
    Next
    INDEX
    Explanations

    occurrences of possessive pronouns and their context in relation to events or entities

    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
    0:0.04
    1:0.05
    2:0.05
    3:0.04
    4:0.05
    5:0.03
    6:0.05
    7:0.48
    8:0.02
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
    ipeg
    -3.45
     Jennings
    -3.14
     Beckham
    -3.12
     Lloyd
    -3.07
    ��
    -3.02
    oyd
    -2.95
     Jewel
    -2.89
     Boyd
    -2.89
     Chandler
    -2.84
     Leica
    -2.73
    POSITIVE LOGITS
    hospital
    2.80
    Wars
    2.69
    caps
    2.68
     Wars
    2.60
     waged
    2.60
    units
    2.57
     waging
    2.53
    wana
    2.50
     caps
    2.49
    fed
    2.48
    Activations Density 0.150%

    No Known Activations