© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 19067
    Prev
    Next
    INDEX
    Explanations

    names of people and entities, particularly those that may be involved in scandalous or controversial situations

    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
    0:0.05
    1:0.30
    2:0.02
    3:0.02
    4:0.01
    5:0.27
    6:0.05
    7:0.01
    8:0.03
    9:0.09
    10:0.05
    11:0.03
    Negative Logits
    serv
    -2.05
    rust
    -2.05
    country
    -2.03
    closed
    -2.02
    package
    -2.02
    tern
    -2.01
    comed
    -2.00
    robe
    -1.99
    swing
    -1.99
    app
    -1.96
    POSITIVE LOGITS
     Seb
    2.05
     Holt
    1.96
     Mou
    1.93
     Ezek
    1.92
     Dion
    1.92
     Ort
    1.91
     Kok
    1.91
     Lug
    1.90
     Dillon
    1.90
     Bou
    1.89
    Activations Density 0.128%

    No Known Activations