© 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. 5-ATT-KK
    6. 19069
    Prev
    Next
    INDEX
    Explanations

    topics related to political controversies and government actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.00
    2:0.15
    3:0.20
    4:0.10
    5:0.03
    6:0.01
    7:0.07
    8:0.10
    9:0.05
    10:0.10
    11:0.10
    Negative Logits
     fuckin
    -1.37
    natureconservancy
    -1.34
    initely
    -1.28
     Fold
    -1.27
     Comparison
    -1.24
    notation
    -1.23
     Defendant
    -1.23
    osite
    -1.23
     Reverse
    -1.23
     Folder
    -1.22
    POSITIVE LOGITS
    AFP
    1.38
     crackdown
    1.30
     blamed
    1.27
     intervene
    1.25
     tourism
    1.25
     AFP
    1.21
    Reuters
    1.20
     boycot
    1.18
     Kremlin
    1.15
     resurg
    1.15
    Activations Density 0.820%

    No Known Activations