© 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. 19425
    Prev
    Next
    INDEX
    Explanations

    references to physical violence and aggression

    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
    0:0.04
    1:0.01
    2:0.05
    3:0.16
    4:0.02
    5:0.06
    6:0.01
    7:0.05
    8:0.03
    9:0.01
    10:0.48
    11:0.02
    Negative Logits
    ITNESS
    -2.38
    ranging
    -2.13
    PN
    -2.13
     continuation
    -2.07
     millenn
    -1.98
    recated
    -1.89
     Pets
    -1.88
     Travels
    -1.84
     consultation
    -1.82
     respect
    -1.81
    POSITIVE LOGITS
     into
    3.15
     onto
    3.08
     overboard
    2.96
     throats
    2.87
     sucker
    2.68
    into
    2.63
     muster
    2.53
     violently
    2.50
     loudly
    2.44
     furiously
    2.43
    Activations Density 0.667%

    No Known Activations