© 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. 10382
    Prev
    Next
    INDEX
    Explanations

    phrases indicating commitment or intention

    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
    2:0.03
    3:0.05
    4:0.06
    5:0.02
    6:0.13
    7:0.47
    8:0.02
    9:0.02
    10:0.06
    11:0.05
    Negative Logits
    DragonMagazine
    -1.84
     Leban
    -1.75
    izens
    -1.73
    TPPStreamerBot
    -1.69
     GOODMAN
    -1.64
    ONSORED
    -1.62
     Zup
    -1.57
     tabl
    -1.54
     Eater
    -1.51
    whe
    -1.48
    POSITIVE LOGITS
    commit
    2.18
     Commit
    2.17
     commitment
    1.97
     allegiance
    1.83
     suicide
    1.81
     undertaking
    1.74
    ensical
    1.71
     Copenhagen
    1.65
     mitigation
    1.65
     committing
    1.64
    Activations Density 0.007%

    No Known Activations