© 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. 10019
    Prev
    Next
    INDEX
    Explanations

    mentions of specific people and events related to current news

    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
    0:0.04
    1:0.07
    2:0.02
    3:0.03
    4:0.02
    5:0.53
    6:0.02
    7:0.01
    8:0.04
    9:0.06
    10:0.05
    11:0.03
    Negative Logits
    castle
    -1.34
    ascript
    -1.29
    works
    -1.28
     [|
    -1.26
    figure
    -1.25
    lik
    -1.25
    425
    -1.24
    hetti
    -1.23
    places
    -1.21
     Facility
    -1.21
    POSITIVE LOGITS
    inventoryQuantity
    1.39
    ITNESS
    1.21
     Abrams
    1.19
    utenberg
    1.15
     Prescott
    1.13
     Rush
    1.12
     Kaine
    1.12
    ilon
    1.11
     resil
    1.10
    aeper
    1.10
    Activations Density 0.415%

    No Known Activations