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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14884
    Prev
    Next
    INDEX
    Explanations

    instances of scandals related to authority figures or institutions

    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
    0:0.10
    1:0.09
    2:0.03
    3:0.04
    4:0.14
    5:0.02
    6:0.11
    7:0.18
    8:0.02
    9:0.04
    10:0.05
    11:0.14
    Negative Logits
     Ideas
    -2.35
     Strong
    -2.18
    IQ
    -2.12
    2200
    -2.08
    uel
    -2.08
     Refugees
    -2.05
    Strong
    -2.04
     Rhythm
    -2.02
    BuyableInstoreAndOnline
    -2.01
    blank
    -1.96
    POSITIVE LOGITS
     scandal
    4.32
     scandals
    4.16
     perjury
    3.07
     wrongdoing
    2.96
    andal
    2.93
     misconduct
    2.88
     Watergate
    2.87
     corruption
    2.87
     bribery
    2.78
     implicated
    2.71
    Activations Density 0.010%

    No Known Activations