© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 27960
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly those of individuals, in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.04
    3:0.05
    4:0.04
    5:0.03
    6:0.44
    7:0.08
    8:0.04
    9:0.07
    10:0.07
    11:0.04
    Negative Logits
    incial
    -1.67
     Cosponsors
    -1.60
    urized
    -1.44
    yip
    -1.36
    psc
    -1.33
    heric
    -1.32
    ngth
    -1.30
    etsk
    -1.28
    iflower
    -1.26
    ormal
    -1.24
    POSITIVE LOGITS
    schild
    1.61
    enegger
    1.57
     Duchess
    1.41
    cliffe
    1.40
    asca
    1.35
     Tsu
    1.33
     Bris
    1.28
    EStream
    1.26
     Tate
    1.22
    DonaldTrump
    1.22
    Activations Density 0.002%

    No Known Activations