© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 8329
    Prev
    Next
    INDEX
    Explanations

    phrases related to manipulation and deceit in political discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.02
    2:0.09
    3:0.33
    4:0.02
    5:0.14
    6:0.01
    7:0.07
    8:0.03
    9:0.01
    10:0.16
    11:0.01
    Negative Logits
     Compass
    -2.04
    ixty
    -1.93
    iple
    -1.93
    angular
    -1.91
    lyss
    -1.86
    imet
    -1.85
     Principles
    -1.83
    RAFT
    -1.81
    itia
    -1.78
    lear
    -1.76
    POSITIVE LOGITS
     discredit
    3.46
     revenge
    3.08
     retribution
    3.00
     animosity
    3.00
     humiliation
    2.90
     hostility
    2.72
     blackmail
    2.71
     disenfranch
    2.70
     unsuspecting
    2.70
     notoriety
    2.69
    Activations Density 0.847%

    No Known Activations