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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 11506
    Prev
    Next
    INDEX
    Explanations

    expressions related to political affiliations and party dynamics

    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
    0:0.03
    1:0.03
    2:0.06
    3:0.04
    4:0.03
    5:0.04
    6:0.15
    7:0.37
    8:0.04
    9:0.03
    10:0.07
    11:0.05
    Negative Logits
    ��
    -1.39
    DragonMagazine
    -1.35
     Doct
    -1.15
     seismic
    -1.11
     largeDownload
    -1.11
    ModLoader
    -1.09
    ヴァ
    -1.09
     awa
    -1.08
     happ
    -1.06
     reverted
    -1.06
    POSITIVE LOGITS
     Caucus
    1.33
    cles
    1.30
    ackets
    1.23
    udeau
    1.22
    rencies
    1.22
    incial
    1.21
    eering
    1.21
     caucus
    1.19
    establishment
    1.18
    bernatorial
    1.17
    Activations Density 0.068%

    No Known Activations