© 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. 23248
    Prev
    Next
    INDEX
    Explanations

    phrases related to volunteering and participation in events

    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
    0:0.20
    1:0.09
    2:0.08
    3:0.04
    4:0.05
    5:0.04
    6:0.09
    7:0.15
    8:0.04
    9:0.04
    10:0.08
    11:0.06
    Negative Logits
    rament
    -2.73
    speech
    -2.63
     ICO
    -2.63
    Crypt
    -2.56
    paio
    -2.50
    CRIP
    -2.48
     Orwell
    -2.42
    iannopoulos
    -2.40
    thereum
    -2.40
     distingu
    -2.36
    POSITIVE LOGITS
     Ryder
    7.41
    Ry
    3.44
     Golf
    3.32
     MLG
    2.98
     Gale
    2.87
     golf
    2.81
     bree
    2.73
     darts
    2.69
     Kelley
    2.68
     Barkley
    2.66
    Activations Density 0.002%

    No Known Activations