© 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. 30245
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names associated with individuals, organizations, or significant entities

    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
    0:0.03
    1:0.02
    2:0.29
    3:0.08
    4:0.08
    5:0.03
    6:0.16
    7:0.04
    8:0.04
    9:0.06
    10:0.08
    11:0.05
    Negative Logits
     prompts
    -1.32
     CES
    -1.30
     downtime
    -1.28
     indoors
    -1.28
     curtains
    -1.27
     shedding
    -1.25
     fences
    -1.25
     tem
    -1.24
    atel
    -1.24
     blo
    -1.23
    POSITIVE LOGITS
    ppa
    1.59
    auri
    1.57
     Ratio
    1.56
    ammy
    1.55
    reau
    1.55
     Nun
    1.53
    agall
    1.46
    rette
    1.45
    龍
    1.44
    vered
    1.42
    Activations Density 0.008%

    No Known Activations