© 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. 2960
    Prev
    Next
    INDEX
    Explanations

    structural elements in written text, particularly related to formatting and organization

    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
    0:0.07
    1:0.03
    2:0.07
    3:0.06
    4:0.04
    5:0.04
    6:0.15
    7:0.05
    8:0.05
    9:0.32
    10:0.05
    11:0.03
    Negative Logits
    bos
    -3.92
     Robbins
    -3.80
     Turk
    -3.64
     Betsy
    -3.54
     Kle
    -3.44
     Bundy
    -3.36
    Ber
    -3.36
     Tuls
    -3.36
    anty
    -3.36
     Cato
    -3.35
    POSITIVE LOGITS
    ign
    6.92
     Ign
    6.86
    Ign
    5.88
    IGN
    5.62
     IGN
    5.58
     Reign
    4.84
     ign
    4.68
     Cogn
    4.17
     ignition
    3.99
     Conquest
    3.81
    Activations Density 0.001%

    No Known Activations