© 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. 9-ATT-KK
    11. 5514
    Prev
    Next
    INDEX
    Explanations

    terms related to different types of chronographs

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.26
    1:0.04
    2:0.09
    3:0.09
    4:0.03
    5:0.08
    6:0.07
    7:0.04
    8:0.11
    9:0.07
    10:0.04
    11:0.02
    Negative Logits
     lettuce
    -3.27
     veggies
    -3.20
    iflower
    -3.19
    SourceFile
    -3.09
    ggies
    -2.96
     cull
    -2.94
     dams
    -2.94
     compost
    -2.91
    Mbps
    -2.90
    keyes
    -2.89
    POSITIVE LOGITS
     Role
    5.20
     Daytona
    3.73
    Role
    3.47
     Rite
    3.21
    role
    3.07
     Magnus
    2.89
     Registry
    2.87
     Monaco
    2.80
    itaire
    2.77
     dial
    2.73
    Activations Density 0.009%

    No Known Activations