© 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. 10-ATT-KK
    11. 17446
    Prev
    Next
    INDEX
    Explanations

    references to damage or harm

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.02
    3:0.04
    4:0.10
    5:0.03
    6:0.03
    7:0.09
    8:0.02
    9:0.08
    10:0.02
    11:0.43
    Negative Logits
    alsa
    -2.42
    audi
    -2.30
     stash
    -2.23
     calendars
    -2.19
    uminati
    -2.12
     Cunning
    -2.07
    doors
    -2.05
    clus
    -2.04
    soDeliveryDate
    -2.03
     WRITE
    -2.02
    POSITIVE LOGITS
     injuries
    4.44
     inflicted
    4.35
     casualties
    4.21
     griev
    3.91
     injury
    3.88
     damage
    3.88
     losses
    3.84
     wounds
    3.74
     humiliation
    3.56
     trauma
    3.52
    Activations Density 0.354%

    No Known Activations