© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 38396
    Prev
    Next
    INDEX
    Explanations

    words related to various forms of illegality or unethical behavior

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.05
    3:0.06
    4:0.07
    5:0.03
    6:0.46
    7:0.04
    8:0.05
    9:0.06
    10:0.05
    11:0.04
    Negative Logits
    kefeller
    -1.40
     Skydragon
    -1.29
    utra
    -1.24
     vendors
    -1.20
    oglu
    -1.18
     Lambert
    -1.18
     Slater
    -1.15
    版
    -1.13
    MAC
    -1.12
     weap
    -1.10
    POSITIVE LOGITS
    akable
    1.88
    cedented
    1.78
    cffffcc
    1.62
    ioned
    1.50
    istant
    1.46
    rupulous
    1.42
    standing
    1.41
    aged
    1.40
    aging
    1.35
    enting
    1.34
    Activations Density 0.023%

    No Known Activations