© 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. 5-ATT-KK
    11. 331
    Prev
    Next
    INDEX
    Explanations

    instances of direct and indirect references to sexual violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.17
    1:0.07
    2:0.07
    3:0.07
    4:0.05
    5:0.08
    6:0.10
    7:0.02
    8:0.09
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
     seiz
    -1.87
     Versus
    -1.62
     Koen
    -1.61
     rooft
    -1.58
     peaked
    -1.56
     Tud
    -1.55
     surges
    -1.53
     KT
    -1.51
     roofs
    -1.50
     Brussels
    -1.48
    POSITIVE LOGITS
    ample
    1.97
    adr
    1.96
    num
    1.94
    later
    1.93
    function
    1.92
    resp
    1.90
    disc
    1.89
    subject
    1.88
    other
    1.88
    desc
    1.86
    Activations Density 0.012%

    No Known Activations