© 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. 19278
    Prev
    Next
    INDEX
    Explanations

    instances of confrontation and insults in interactions

    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
    0:0.18
    1:0.07
    2:0.09
    3:0.05
    4:0.05
    5:0.04
    6:0.10
    7:0.06
    8:0.03
    9:0.07
    10:0.15
    11:0.04
    Negative Logits
    Harris
    -4.01
     Harris
    -3.84
     Abbas
    -3.45
    HOU
    -3.36
    gypt
    -3.31
    EH
    -3.29
     Aad
    -3.24
    Houston
    -3.12
    Rah
    -3.10
    ption
    -3.06
    POSITIVE LOGITS
     Coco
    9.61
     Velvet
    9.19
    elvet
    5.01
     Pyrrha
    4.90
     cocoa
    4.67
     Coc
    4.58
     Puppet
    4.26
     Chocolate
    4.20
     velvet
    4.19
     Ruby
    4.11
    Activations Density 0.002%

    No Known Activations