© 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. 16770
    Prev
    Next
    INDEX
    Explanations

    references to concepts or themes described as "whole."

    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
    1:0.03
    2:0.28
    3:0.07
    4:0.12
    5:0.04
    6:0.06
    7:0.05
    8:0.05
    9:0.05
    10:0.08
    11:0.07
    Negative Logits
     incarn
    -1.86
     SPR
    -1.84
     Fren
    -1.80
     Fang
    -1.74
     Pier
    -1.72
     Pieces
    -1.72
     Cher
    -1.63
     Ultr
    -1.58
     Bucc
    -1.51
     HIT
    -1.50
    POSITIVE LOGITS
    Reviewer
    2.43
    rency
    2.33
    merce
    2.19
    ignty
    2.07
    Cause
    1.99
    DragonMagazine
    1.96
     guiActiveUn
    1.89
    Topic
    1.86
    allery
    1.85
    NetMessage
    1.84
    Activations Density 0.021%

    No Known Activations