© 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. 39835
    Prev
    Next
    INDEX
    Explanations

    references to images and media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.05
    3:0.13
    4:0.09
    5:0.02
    6:0.07
    7:0.30
    8:0.04
    9:0.04
    10:0.07
    11:0.11
    Negative Logits
    answered
    -1.64
     QUEST
    -1.51
    phabet
    -1.45
    シャ
    -1.44
    answer
    -1.44
     queries
    -1.44
     particulars
    -1.43
    -|
    -1.36
    holiday
    -1.34
    eday
    -1.34
    POSITIVE LOGITS
     Poker
    1.43
     Roller
    1.33
     Huck
    1.31
     fram
    1.30
     Gavin
    1.27
     scoreboard
    1.27
     Shutterstock
    1.21
     Wad
    1.20
     Carnegie
    1.20
    ���
    1.20
    Activations Density 0.016%

    No Known Activations