© 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. 21618
    Prev
    Next
    INDEX
    Explanations

    references to influential individuals and their roles in significant contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.09
    3:0.04
    4:0.09
    5:0.03
    6:0.06
    7:0.39
    8:0.02
    9:0.03
    10:0.10
    11:0.06
    Negative Logits
     guiActiveUnfocused
    -1.99
     externalToEVAOnly
    -1.68
     Results
    -1.56
    Normal
    -1.51
     Related
    -1.50
     Decre
    -1.45
    affected
    -1.45
     Updates
    -1.44
     impairment
    -1.43
     PsyNet
    -1.43
    POSITIVE LOGITS
    igne
    1.63
    amiya
    1.55
     Bir
    1.50
    enne
    1.49
     Berger
    1.48
    zzi
    1.48
    cci
    1.47
    zel
    1.46
    chel
    1.45
     impecc
    1.43
    Activations Density 0.025%

    No Known Activations