© 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. 10-ATT-KK
    11. 21063
    Prev
    Next
    INDEX
    Explanations

    mentions of political affiliations and connections

    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
    0:0.20
    1:0.05
    2:0.04
    3:0.06
    4:0.04
    5:0.03
    6:0.19
    7:0.12
    8:0.03
    9:0.03
    10:0.11
    11:0.05
    Negative Logits
     debtor
    -3.44
    natureconservancy
    -3.33
     Zeal
    -3.26
     Manit
    -2.97
    velop
    -2.85
     Slayer
    -2.84
     Pip
    -2.76
     Rubber
    -2.71
     STL
    -2.71
     bom
    -2.71
    POSITIVE LOGITS
     Nunes
    7.92
     Schiff
    4.15
     Intelligence
    3.38
     Priebus
    3.36
     Beir
    3.35
    intelligence
    3.25
     unm
    3.24
     McCarthy
    3.15
     FISA
    3.06
     intel
    3.04
    Activations Density 0.001%

    No Known Activations