Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14717
    Prev
    Next
    INDEX
    Explanations

    references to denial of service attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.06
    2:0.06
    3:0.06
    4:0.07
    5:0.03
    6:0.19
    7:0.08
    8:0.03
    9:0.05
    10:0.14
    11:0.09
    Negative Logits
     EB
    -2.87
     ABE
    -2.73
    yip
    -2.73
     Strongh
    -2.66
     CAT
    -2.61
     forestry
    -2.54
     Crate
    -2.47
    BALL
    -2.46
     Cay
    -2.45
    eligible
    -2.43
    POSITIVE LOGITS
    Writ
    3.20
    oston
    2.87
    Adams
    2.82
     Nort
    2.76
    sf
    2.74
     Oath
    2.72
    DOS
    2.71
     Sons
    2.63
    tumblr
    2.58
     TED
    2.52
    Activations Density 0.000%

    No Known Activations