© 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 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. 12907
    Prev
    Next
    INDEX
    Explanations

    references to allegations of sexual misconduct or inappropriate behavior

    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
    0:0.14
    1:0.03
    2:0.24
    3:0.07
    4:0.03
    5:0.13
    6:0.07
    7:0.05
    8:0.05
    9:0.06
    10:0.05
    11:0.03
    Negative Logits
     Suicide
    -3.51
     Deaths
    -3.26
    icidal
    -3.25
     suicide
    -3.22
     pestic
    -3.15
     homicide
    -2.98
    icide
    -2.92
    violence
    -2.91
     Violent
    -2.89
     Killing
    -2.89
    POSITIVE LOGITS
     grop
    4.50
    Grab
    3.53
    grab
    3.25
     Grab
    2.85
     inappropriately
    2.77
     baggage
    2.77
     lifts
    2.68
     fav
    2.56
    Magn
    2.55
     grabbing
    2.54
    Activations Density 0.002%

    No Known Activations