© 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. 33488
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negative consequences or bad outcomes

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.08
    3:0.06
    4:0.11
    5:0.02
    6:0.05
    7:0.42
    8:0.03
    9:0.02
    10:0.06
    11:0.08
    Negative Logits
    ItemImage
    -1.51
    ominated
    -1.49
    soType
    -1.48
    riott
    -1.48
    umn
    -1.44
    hare
    -1.42
    orney
    -1.38
    ledged
    -1.38
    zona
    -1.38
    Square
    -1.37
    POSITIVE LOGITS
     counterfe
    1.67
     leaks
    1.58
     sabot
    1.58
     digestion
    1.57
     malf
    1.54
     retard
    1.53
    dies
    1.47
     Poor
    1.44
     degener
    1.44
     Corruption
    1.44
    Activations Density 0.038%

    No Known Activations