© 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. 3-ATT-KK
    11. 14252
    Prev
    Next
    INDEX
    Explanations

    rarity categories or statuses in a collection or hierarchy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to rarity and classification status in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.09
    2:0.09
    3:0.10
    4:0.07
    5:0.06
    6:0.05
    7:0.10
    8:0.08
    9:0.08
    10:0.08
    11:0.09
    Negative Logits
     Eug
    -1.08
    GUI
    -1.07
     soap
    -1.06
    metic
    -1.02
     certific
    -1.01
     Innocent
    -1.01
     anus
    -1.01
     compost
    -0.99
     manif
    -0.99
     Sed
    -0.99
    POSITIVE LOGITS
    alam
    1.27
     Kraken
    1.20
    inav
    1.17
    aeda
    1.15
    aroo
    1.14
    negie
    1.13
    eah
    1.12
     Lilly
    1.12
    ocobo
    1.08
     [&
    1.07
    Activations Density 0.005%

    No Known Activations