© 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. 10505
    Prev
    Next
    INDEX
    Explanations

    names or references to notable individuals, particularly those starting with "K" or "Mc"

    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
    0:0.08
    1:0.05
    2:0.05
    3:0.08
    4:0.04
    5:0.05
    6:0.15
    7:0.04
    8:0.07
    9:0.26
    10:0.04
    11:0.04
    Negative Logits
    Ed
    -3.63
     Edwards
    -3.28
     McH
    -3.09
    yss
    -3.05
    ellen
    -3.01
    Ell
    -2.92
     DeL
    -2.90
    Attach
    -2.82
     Ed
    -2.80
    aud
    -2.77
    POSITIVE LOGITS
     Zeus
    3.38
     Zoro
    3.01
    Roman
    2.88
     Gutenberg
    2.87
     generator
    2.60
     Croatian
    2.60
     Kot
    2.58
     shaman
    2.56
     Pagan
    2.55
     Romantic
    2.53
    Activations Density 0.000%

    No Known Activations