© 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. 11100
    Prev
    Next
    INDEX
    Explanations

    instances of censorship or removal of content

    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
    1:0.08
    2:0.07
    3:0.08
    4:0.08
    5:0.08
    6:0.08
    7:0.09
    8:0.08
    9:0.09
    10:0.08
    11:0.07
    Negative Logits
     carriage
    -2.74
     print
    -2.64
     luggage
    -2.52
     packaging
    -2.46
     suitcase
    -2.44
     :-)
    -2.44
     donkey
    -2.44
     messenger
    -2.41
    ...)
    -2.40
     pony
    -2.40
    POSITIVE LOGITS
    ォ
    3.47
     Geh
    3.31
    inventoryQuantity
    2.97
    田
    2.94
    ゴン
    2.93
    龍喚士
    2.90
    Arc
    2.88
    BuyableInstoreAndOnline
    2.87
    NetMessage
    2.86
    ��
    2.82
    Activations Density 0.000%

    No Known Activations