© 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. 3-ATT-KK
    11. 5395
    Prev
    Next
    INDEX
    Explanations

    references to individuals' places of birth and their professions or roles

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.05
    3:0.03
    4:0.03
    5:0.07
    6:0.08
    7:0.17
    8:0.11
    9:0.03
    10:0.06
    11:0.23
    Negative Logits
     amplification
    -1.61
     intervals
    -1.39
     insertion
    -1.30
     suscept
    -1.29
    erences
    -1.28
    ◼
    -1.27
    SPONSORED
    -1.26
     saturation
    -1.25
     thresholds
    -1.23
    arson
    -1.19
    POSITIVE LOGITS
    oan
    1.43
     WOM
    1.30
     Jane
    1.23
    irlf
    1.20
    adan
    1.18
     Wife
    1.17
     labou
    1.16
     Mahar
    1.12
    ¢
    1.11
    anga
    1.11
    Activations Density 0.003%

    No Known Activations