© 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. 21284
    Prev
    Next
    INDEX
    Explanations

    references to crime and criminal activity

    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
    0:0.09
    1:0.42
    2:0.04
    3:0.03
    4:0.03
    5:0.11
    6:0.04
    7:0.02
    8:0.04
    9:0.05
    10:0.04
    11:0.04
    Negative Logits
    122
    -2.16
     Constable
    -2.14
    ensation
    -2.13
    ract
    -2.12
    121
    -2.11
    CV
    -2.07
    onduct
    -2.04
    transfer
    -2.04
    HR
    -2.01
    entin
    -1.95
    POSITIVE LOGITS
     freak
    2.08
     Zombie
    2.00
     zombie
    2.00
     scary
    1.97
     crazy
    1.96
     cheesy
    1.96
    yip
    1.95
     lame
    1.89
     Rocky
    1.89
     mob
    1.88
    Activations Density 0.048%

    No Known Activations