© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15854
    Prev
    Next
    INDEX
    Explanations

    statements regarding organized and sophisticated hacking activities

    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
    0:0.16
    1:0.09
    2:0.08
    3:0.06
    4:0.04
    5:0.01
    6:0.08
    7:0.14
    8:0.02
    9:0.04
    10:0.17
    11:0.05
    Negative Logits
     forgiven
    -2.80
     Kelvin
    -2.79
     Bauer
    -2.62
    Scotland
    -2.60
    Northern
    -2.60
    LG
    -2.48
     bung
    -2.46
    gat
    -2.44
     graft
    -2.40
     mole
    -2.40
    POSITIVE LOGITS
     Sym
    7.19
    sym
    5.69
    Sym
    5.62
     sym
    5.24
    Sys
    3.70
     SY
    3.16
     Som
    3.11
     Psy
    3.00
    sys
    2.99
     Sar
    2.88
    Activations Density 0.003%

    No Known Activations