© 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. 16830
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical operations or numerical adjustments

    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
    0:0.04
    1:0.04
    2:0.04
    3:0.07
    4:0.09
    5:0.04
    6:0.04
    7:0.08
    8:0.04
    9:0.05
    10:0.09
    11:0.32
    Negative Logits
    schild
    -2.61
    gebra
    -2.36
    uations
    -2.32
    lections
    -2.30
    alsh
    -2.26
    ourgeois
    -2.23
    renheit
    -2.21
    baum
    -2.20
    aunder
    -2.20
    tsky
    -2.12
    POSITIVE LOGITS
    RAW
    2.39
     invaders
    1.92
     venom
    1.88
     carc
    1.86
     fiercely
    1.78
     pirates
    1.77
     Federation
    1.77
     jaws
    1.70
     claws
    1.69
     invasion
    1.69
    Activations Density 0.000%

    No Known Activations