© 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. 9-ATT-KK
    11. 23455
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal consequences and mandated actions following offenses

    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
    0:0.06
    1:0.02
    2:0.16
    3:0.13
    4:0.04
    5:0.16
    6:0.02
    7:0.13
    8:0.05
    9:0.02
    10:0.14
    11:0.02
    Negative Logits
     Assass
    -2.27
     monop
    -2.19
     assassinated
    -2.12
    Origin
    -2.04
     assassination
    -1.95
    emen
    -1.91
     assass
    -1.91
     Cyr
    -1.88
     assassins
    -1.87
     Franch
    -1.84
    POSITIVE LOGITS
     probation
    2.82
     restitution
    2.46
     rehabilit
    2.27
     rehabilitation
    2.19
     repairs
    2.15
     reconnect
    2.07
     curfew
    2.03
    wx
    2.01
    learning
    2.00
     counseling
    1.98
    Activations Density 0.015%

    No Known Activations