© 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. 10-ATT-KK
    11. 15429
    Prev
    Next
    INDEX
    Explanations

    instances of people, proper names, and numerical references in the text

    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
    0:0.06
    1:0.03
    2:0.04
    3:0.03
    4:0.03
    5:0.02
    6:0.02
    7:0.48
    8:0.03
    9:0.03
    10:0.15
    11:0.03
    Negative Logits
    Jew
    -2.75
     crow
    -2.60
     sun
    -2.50
    Tes
    -2.50
     ram
    -2.48
     jew
    -2.33
     Rothschild
    -2.32
     vap
    -2.27
    RAM
    -2.25
     Bomb
    -2.22
    POSITIVE LOGITS
    achelor
    2.54
     Grac
    2.33
    accompan
    2.30
    adies
    2.29
    arer
    2.27
     Salary
    2.26
     Feder
    2.23
     Mercenary
    2.22
    154
    2.17
    atha
    2.17
    Activations Density 0.072%

    No Known Activations