© 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. 9-ATT-KK
    11. 18872
    Prev
    Next
    INDEX
    Explanations

    multi-part structures or sequences in contexts involving rules and instructions

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

    No Comments

    Head Attr Weights
    0:0.05
    1:0.03
    2:0.04
    3:0.07
    4:0.03
    5:0.04
    6:0.10
    7:0.03
    8:0.03
    9:0.46
    10:0.03
    11:0.03
    Negative Logits
     Ing
    -3.75
    edin
    -3.75
    zyme
    -3.05
     Rodgers
    -3.01
    hall
    -2.96
     Rubin
    -2.93
     Dug
    -2.91
    Ed
    -2.88
    Ing
    -2.88
    sen
    -2.78
    POSITIVE LOGITS
     Cloud
    3.40
     Cart
    3.11
    Cloud
    3.07
    ilo
    3.02
     Bron
    3.00
    Pocket
    2.99
    Cart
    2.97
     coc
    2.96
     Pocket
    2.88
     loops
    2.84
    Activations Density 0.015%

    No Known Activations