© 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. 10-ATT-KK
    6. 14133
    Prev
    Next
    INDEX
    Explanations

    phrases related to Reagan's government policies and their impact

    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
    0:0.19
    1:0.07
    2:0.05
    3:0.12
    4:0.04
    5:0.02
    6:0.12
    7:0.15
    8:0.01
    9:0.05
    10:0.08
    11:0.04
    Negative Logits
     Ox
    -3.20
    Arsenal
    -2.99
     Aus
    -2.93
     Artemis
    -2.92
    liga
    -2.82
     Zhang
    -2.76
    ortmund
    -2.74
     Beng
    -2.74
     Emirates
    -2.72
     Mumbai
    -2.69
    POSITIVE LOGITS
     Reagan
    7.48
     Ronald
    4.82
     Thatcher
    4.08
    Bush
    3.75
     Eisenhower
    3.69
     Bush
    3.65
     Nixon
    3.60
     1981
    3.46
     1983
    3.45
    Ron
    3.45
    Activations Density 0.019%

    No Known Activations