© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10893
    Prev
    Next
    INDEX
    Explanations

    information about notable individuals and their contributions

    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
    0:0.17
    1:0.03
    2:0.22
    3:0.07
    4:0.03
    5:0.07
    6:0.03
    7:0.06
    8:0.16
    9:0.03
    10:0.03
    11:0.04
    Negative Logits
    mble
    -3.41
    覚醒
    -3.29
    wcsstore
    -3.29
    merga
    -3.17
     Ramsay
    -3.08
     Beir
    -3.06
    ocobo
    -2.98
     Loch
    -2.98
    ignty
    -2.91
    rolet
    -2.79
    POSITIVE LOGITS
    artz
    4.20
     hacker
    4.14
     Gmail
    4.06
     MIT
    3.98
     GitHub
    3.87
     downloading
    3.76
     AOL
    3.69
     Wikileaks
    3.63
     Hacker
    3.59
     Wired
    3.58
    Activations Density 0.002%

    No Known Activations