© 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. 9868
    Prev
    Next
    INDEX
    Explanations

    negative actions or consequences associated with personal behaviors or attacks

    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
    0:0.05
    1:0.03
    2:0.09
    3:0.06
    4:0.04
    5:0.05
    6:0.21
    7:0.02
    8:0.07
    9:0.27
    10:0.03
    11:0.04
    Negative Logits
     Reynolds
    -3.98
     Vaugh
    -3.97
     Lima
    -3.33
     Holland
    -3.28
     Recre
    -3.25
     cords
    -3.23
     Pratt
    -3.22
     Grim
    -3.21
     Newport
    -3.21
     Vin
    -3.19
    POSITIVE LOGITS
     Attack
    6.68
    Attack
    6.42
    attack
    5.97
     attack
    5.92
     attacks
    5.88
     assaults
    5.75
    attacks
    5.64
     Attacks
    5.55
     assault
    5.32
     attackers
    5.23
    Activations Density 0.009%

    No Known Activations