© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 6935
    Prev
    Next
    INDEX
    Explanations

    topics related to political campaigns and scandals

    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
    0:0.04
    1:0.03
    2:0.07
    3:0.06
    4:0.02
    5:0.03
    6:0.26
    7:0.22
    8:0.06
    9:0.03
    10:0.06
    11:0.06
    Negative Logits
     cryst
    -1.50
    theless
    -1.43
    ateurs
    -1.42
    龍喚士
    -1.36
     condu
    -1.19
    Height
    -1.12
    fitting
    -1.12
    tenance
    -1.09
    esa
    -1.09
    adequ
    -1.08
    POSITIVE LOGITS
     Cyn
    1.48
    bernatorial
    1.42
     Award
    1.32
     Bridge
    1.30
    mma
    1.29
     Himself
    1.29
     veto
    1.26
     Airport
    1.25
    iasco
    1.25
    undrum
    1.25
    Activations Density 0.104%

    No Known Activations