© 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. 12277
    Prev
    Next
    INDEX
    Explanations

    references to trolling, internet behavior, and the impact of such actions on conversations

    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
    0:0.30
    1:0.03
    2:0.12
    3:0.09
    4:0.03
    5:0.08
    6:0.04
    7:0.04
    8:0.06
    9:0.05
    10:0.06
    11:0.04
    Negative Logits
     Quint
    -2.24
    eele
    -2.23
     aisle
    -2.22
     Cinem
    -2.18
    rolet
    -2.18
    ér
    -2.18
     Creed
    -2.18
    robe
    -2.16
     ELE
    -2.14
    enger
    -2.12
    POSITIVE LOGITS
     trolling
    4.95
     troll
    4.81
     trolls
    4.46
     Troll
    3.46
    Tumblr
    2.93
     harassing
    2.90
     spam
    2.88
     Torrent
    2.83
     Tumblr
    2.79
    DoS
    2.79
    Activations Density 0.002%

    No Known Activations