© 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. 9424
    Prev
    Next
    INDEX
    Explanations

    references to violence and aggression

    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
    0:0.06
    1:0.03
    2:0.02
    3:0.04
    4:0.18
    5:0.07
    6:0.04
    7:0.32
    8:0.02
    9:0.10
    10:0.03
    11:0.05
    Negative Logits
    trak
    -2.92
     guiActiveUn
    -2.70
    Rocket
    -2.57
    Rush
    -2.52
    achy
    -2.50
    Psy
    -2.41
    zar
    -2.35
     optimism
    -2.34
     Ratio
    -2.31
    arton
    -2.30
    POSITIVE LOGITS
    AppData
    2.74
     Coulter
    2.70
     mist
    2.50
     Citiz
    2.48
     sexually
    2.38
     cabbage
    2.35
     retali
    2.35
     Godd
    2.35
     swore
    2.33
     cunt
    2.33
    Activations Density 0.100%

    No Known Activations