© 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. 10-ATT-KK
    11. 16783
    Prev
    Next
    INDEX
    Explanations

    terms related to propaganda and its impact on public perception and behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.03
    2:0.04
    3:0.06
    4:0.13
    5:0.03
    6:0.13
    7:0.16
    8:0.02
    9:0.07
    10:0.04
    11:0.14
    Negative Logits
    �
    -2.65
    --+
    -2.52
    eca
    -2.51
    Oracle
    -2.48
     Pebble
    -2.30
    uci
    -2.29
    aceae
    -2.25
    orem
    -2.16
    angered
    -2.14
    juries
    -2.13
    POSITIVE LOGITS
     propaganda
    5.50
     disinformation
    4.56
    aganda
    4.54
     propag
    4.34
     indoctr
    3.90
     leaflets
    3.47
     Kremlin
    3.45
     indo
    3.42
     censorship
    3.40
     pamph
    3.34
    Activations Density 0.026%

    No Known Activations